Xintao Wang @xinntao
Senior Staff Researcher at Tencent ARC Lab and Tencent AI Lab. PhD from MMLab, CUHK. xinntao.github.io Joined August 2017-
Tweets86
-
Followers614
-
Following170
-
Likes164
Woah, this worked so much better than I expected
Woah, this worked so much better than I expected https://t.co/4K4hzxCt5P
Thanks @_akhaliq for promoting our work! Our PhysDreamer synthesizes physically-interactable 3D objects. Play with your favorite soft objects🌹🪴🌿. Project website: physdreamer.github.io
Thanks @_akhaliq for promoting our work! Our PhysDreamer synthesizes physically-interactable 3D objects. Play with your favorite soft objects🌹🪴🌿. Project website: physdreamer.github.io
🤯 This is insane Simulon can add any 3D model to your real footage video in a matter of minutes. It's so real that I almost can touch it!
Unlock long #video generation at a lower cost with keyframe generation and #InstantSplat! 📸Leveraging 12 key frames from the #Sora video (#Santorini ), we perform pose-free 3D modeling with InstantSplat. ⚡️Training in 40 seconds with an #A100 GPU. ✍️Efficient rendering of…
Adobe presents VideoGigaGAN! A new video upscaling model that can upsample a video up to 8x with rich details. 10 wild examples ⬇️
Thanks to @_akhaliq for sharing! Check out SEED-X, your virtual assistant, the latest in our SEED series. It's a multimodal foundation model designed for real-world tasks (see attached images) that unifies understanding and generation. 🤩 Project page: github.com/AILab-CVC/SEED…
Thanks to @_akhaliq for sharing! Check out SEED-X, your virtual assistant, the latest in our SEED series. It's a multimodal foundation model designed for real-world tasks (see attached images) that unifies understanding and generation. 🤩 Project page: github.com/AILab-CVC/SEED… https://t.co/jyZWnb7jCz
Check our MeshLRM work for fast sparse-view mesh reconstruction! We showed the power of decoder-only transformer and context expansion (similar to LLMs), and diff. marching cubes! Great collaboration between UCSD (@SarahWeii, @haosu_twitr ) and Adobe Research!
Check our MeshLRM work for fast sparse-view mesh reconstruction! We showed the power of decoder-only transformer and context expansion (similar to LLMs), and diff. marching cubes! Great collaboration between UCSD (@SarahWeii, @haosu_twitr ) and Adobe Research!
lonely ~ meta ai
So excited that our 𝗗𝘆𝗻𝗮𝗺𝗶𝗖𝗿𝗮𝗳𝘁𝗲𝗿-𝟭𝟬𝟮𝟰 ranks 𝟭𝘀𝘁 on the I2V benchmark list from VBench!
Thanks @_akhaliq , @liuziwei7! Glad to see our I2V DynamiCrafter at Top1, and t2V VideoCrafter2 at Top3 on your VBench leaderboard.
Thanks @_akhaliq , @liuziwei7! Glad to see our I2V DynamiCrafter at Top1, and t2V VideoCrafter2 at Top3 on your VBench leaderboard. https://t.co/dSpM9Ea8Qx
Kicked off the AI session at TED on Tuesday with this video I made with Sora to imagine what 40 more years of TED might look like
Kicked off the AI session at TED on Tuesday with this video I made with Sora to imagine what 40 more years of TED might look like
Finetuning YOLO-World in one line 🤩
🤯InstantMesh from Tencent is insane - Super fast Image-to-3D with high quality output ⬇️ Link below - Generate a 3D model from a single image in 30 seconds for free 🔥🔥
🎨Spent some time refactoring the 2021 post on diffusion model with new content: lilianweng.github.io/posts/2021-07-… ⬇️ ⬇️ ⬇️ 🎬Then another short piece on diffusion video models: lilianweng.github.io/posts/2024-04-… (Yes, I had an intensive weekend🥹)
🎉We are exploring the #Mira project~ - Built a long video dataset #MiraData with structured captions. - Trained #MiraDiT to explore the consistency in long video generation. Hope it will be a supplement to existing text-to-video methods. Project Page: mira-space.github.io
#InstantMesh🎉, an image-to-3D mesh generation method from a single image within 10 seconds. Incorporate mesh-based optimization, better training efficiency, and scalability, allowing explicit geometric supervision. Codes: github.com/TencentARC/Ins… Demo: huggingface.co/spaces/Tencent…
Our CVPR24 highlights: SmartEdit: Exploring Complex Instruction-based Image Editing with LLMs Programmable Motion Generation for Open-set Motion Control Tasks HumanGaussian: Text-Driven 3D Human Generation with GS Turns out there's no overlap with the ones listed earlier😆😆
Our CVPR24 highlights: SmartEdit: Exploring Complex Instruction-based Image Editing with LLMs Programmable Motion Generation for Open-set Motion Control Tasks HumanGaussian: Text-Driven 3D Human Generation with GS Turns out there's no overlap with the ones listed earlier😆😆
CustomNet demo is online: huggingface.co/spaces/Tencent… customize your objects with controllable viewpoints~
CustomNet demo is online: huggingface.co/spaces/Tencent… customize your objects with controllable viewpoints~
Segment and Edit Anything, on your Local Computer. The Brushnet Gradio app lets you select some points in an image to segment items, and replace them with ANYTHING you want. Pure magic. And now, run locally on your machine with 1 click. Works on all OS (Windows, Mac, Linux)
Segment and Edit Anything, on your Local Computer. The Brushnet Gradio app lets you select some points in an image to segment items, and replace them with ANYTHING you want. Pure magic. And now, run locally on your machine with 1 click. Works on all OS (Windows, Mac, Linux) https://t.co/QmBPPhVH52
Zhihao Zhao @ZhihaoZ33738217
39 Followers 169 FollowingJohanne Mcraney @JohanneMcr18833
73 Followers 5K Followingbj w @wangbingjie1989
29 Followers 396 Followingpengfei YAO @Huihui89688
25 Followers 37 FollowingTimothée Coolamet @KaladinFree
15K Followers 767 Following Christian, husband, father. Independent. Cybertruck Enthusiast. Jack Smith fan club. Blocker of gnat accounts. #DoNotUnite🚫 #BreakTheCult #BurnItDownRicardo López @Rirsc_
136 Followers 1K FollowingNirvana.Viaje @NirViaje
703 Followers 4K Following Math, Complex System, Political Science, Circuit and HAM, Cycling, Piano.. .etcShavon Pabon @PabSha
29 Followers 5K FollowingTanvir Mahmud @TanvirMahmud32
63 Followers 384 Following PhD Student, Multi-modal Learning, The University of Texas at AustinChonghao Sima @smch_1127
53 Followers 221 Following Autonomous Driving & "Foundation" model at @OpenDriveLab and @HKUniversity (previously ML4Science at @LifeAtPurdue)Xiang Fu @thisisxfu
45 Followers 2K Following Researcher @BUSPH | @BU_CDS | Founder of @ModularNLP | Deep Learning | Data Science |Azucena Croasmun @croas_azuc
69 Followers 5K FollowingLydia Acor @acor_ly
28 Followers 5K Followingxiwuxuewei @xiwuxuewei
1 Followers 45 FollowingLu Sheng @SHENGLui1989
77 Followers 130 Following I am an Associate Professor at Beihang University, focusing on 3D computer vision. I am the PI of Kaleidoscope Laboratory at Beihang University.Cameron Priestley @filthy_priest
116 Followers 774 Followingdwdw dw @dwdwdw867169
1 Followers 43 Followingavinash badaramoni @ABadaramoni
2 Followers 54 FollowingHan Lin @hanlin_hl
294 Followers 612 Following PhD student at @UNCCS @UNCNLP MURGe-Lab. Video Generation, Generative Models, Multimodal Learning, and LLMsYuAng @yuanggnaw
37 Followers 919 FollowingOtoMAN @AnikiRip
1K Followers 934 Following CTO and co-founder @figura_labs | ex-LinkedIn, former SRE specializing in extremely high traffic (1b+ users) distributed systems | views are my ownFun xx @Funxx64756245
22 Followers 97 Followingoouul @wawatataww
15 Followers 345 Followingjooeyzz @jooeyzz
127 Followers 3K Followingtyler-huang @tyler_jack_s1
7 Followers 279 FollowingErvinA @ervina754788336
9 Followers 57 FollowingSpaceman @SpacemanTheDJen
2K Followers 1K Following 'Ad Futurum Per Technologiam' Serial Founder @metafintek | @elysium1337kuta | @strandsnation Noob Coder | Dad | Dude | DJ e/acc #LFG #YNWAAIOcto @aiocto
129 Followers 1K Following Exploring the limitless possibilities of AI, STEM, R&D, Art and creativity to craft works that engage and inspire, and challenge the status quo.Vivek Srivastava @vivek_genai
808 Followers 510 Following CMO @AppyPieInc. Appy Pie is a leading No-Code platform with 10 Million+ users.savin @savin198
18 Followers 156 Followingconan1024hao @810396815
906 Followers 1K Following MS student @waseda_univ @nlp_waseda | Ex-intern @legalontech_jp @omron_sinicx @cyberagent_ai @LINECorp_jp @mcdigital_mcd | NLP, Multimodalinvestandbeyond @investandbeyond
40 Followers 230 FollowingZhongkai Zhao @zzk_zhao
46 Followers 244 Following Master of Computing @ NUS SoC MLSys | HPC | LLM | SE4AIloongxl @loongxl
54 Followers 1K FollowingPatric Gutersohn @GutersohnPatric
125 Followers 219 Following Fullstack Developer who has a favor for Web 3.0 DApps on MultiverX. The future belongs to the curious.KevinBoy🇺🇦 @apple163995
61 Followers 298 FollowingNick St. Pierre @nickfloats
157K Followers 2K Following Creative Director and unofficial Midjourney shill. Publicly exploring AI & sharing learnings.AGI House @agihouse_org
13K Followers 414 Following Accelerating humanity's transition to AGI & honoring the greatest AI founders and researchers of our time @ https://t.co/1lJUc58gZJjuju @juxuan_27
87 Followers 83 Following Ph.D. Candidate @cuhkcse, Research Intern @TencentGlobal ARC, Previous Intern @IDEA, @SenseTime_AISaining Xie @sainingxie
14K Followers 1K Following researcher in #deeplearning #computervision | assistant professor at @NYU_Courant @nyuniversity | previous: research scientist @metaai (FAIR) @UCSanDiegoKelvin Chan @kelvinckchan
681 Followers 107 Following Research Scientist @GoogleAI. Working on image/video generation, editing, and restoration.Kaiyang Zhou @kaiyangzhou
1K Followers 381 Following Assistant Professor at HKBU. Interested in machine learning & computer vision.Tai Wang @wangtai97
426 Followers 343 Following Researcher at OpenRobotLab, Shanghai AI Lab. PhD from MMLab, CUHK.chong mou @eechongmou
6 Followers 9 FollowingJinbo Xing @Double47685693
131 Followers 23 Following A third-year Ph.D. student at The Chinese University of Hong Kong. I'm interested in AIGC (especially video generation).Min Choi @minchoi
66K Followers 762 Following AI Educator. 𝕏 about AI, solutions and interesting things. Showing how to leverage AI in practical ways for you and your business.He Zhang @zhanghesprinter
327 Followers 220 Following Senior Research Scientist @ Adobe Research. “old” student athlete for 100&200MNicolas Neubert @iamneubert
37K Followers 476 Following ✨Redefining the future of storytelling at @runwayml. 💎 Daily AI insights. 🪄Prompting in public.Longyue Wang @wangly0229
889 Followers 454 Following Dr. | Research Fellow @ Tencent AI Lab | IEEE Senior Member | Previously @DCU PhD & RA, @TencentGlobal InternRichard @RichardXia101
9 Followers 34 Following Computer vision and deep learning researcher at Tencent AI lab.Yong Norris Zhang @Norris29973102
71 Followers 186 FollowingXia Zhou @ZhouXia1212
14 Followers 26 FollowingYuliang Xiu @yuliangxiu
5K Followers 4K Following Ph.D. in Vision & Graphics @MPI_IS, previously @USC_ICT. Focusing on democratizing human-centric digitization. Intern at @RealityLabs @Ubisoftcamenduru @camenduru
15K Followers 4K Following ML & Computer Engineer, Game Designer. #OpenSource ❤ #UE ❤ #Jupyter ❤ #AI #ML #StableDiffusion #LLM #NeRF #GaussianSplatting #T2V https://t.co/8MMNbygz1PXiaodong Cun @shadocun
269 Followers 182 Following Here's to the Crazy Ones. || Animating pixels. || works on #SadTalker #VideoReTalking #VideoCrafter || Computer Vision/Graphics ResearcherXiaoguang Han @XiaogHan
534 Followers 556 Following Assistant Professor at SSE, The Chinese University of Hong Kong,Shenzhen. Working in the area of Computer Vision and Computer Graphics.Tiezhen WANG @Xianbao_QIAN
916 Followers 349 Following Engineer at HuggingFace, ex-Googler on TFLite / micro. Ideas are my own.Sasha Rush @srush_nlp
52K Followers 464 Following Professor, Programmer in NYC. Cornell Tech, Hugging Face 🤗 https://t.co/cZl0wTfqGzSylvain Gugger @GuggerSylvain
22K Followers 341 Following All things Machine Learning Previously at @huggingface and @fastdotai Co-author of https://t.co/lywnOAwwnc He/himJulien Chaumond @julien_c
47K Followers 1K Following Co-founder and CTO at @huggingface 🤗. ML/AI for everyone, building products to propel communities fwd. @Stanford + @PolytechniqueOmar Sanseviero @osanseviero
31K Followers 2K Following Chief Llama Officer @huggingface 🦙 Founder @AI_Learners. Xoogler (SWE @Google Assistant, 20% PM TF Graphics). 100% Hacker Llama🇵🇪🇲🇽Zhongang Cai @caizhongang
525 Followers 171 Following Ph.D. Student at MMLab@NTU Senior Algorithm Researcher, SenseTimeXiangyu Xu @JohnXu_2015
215 Followers 282 Following Professor @ Xi'an Jiaotong University Computer Vision and Machine Learning Home: https://t.co/I5GHOom0GSclem 🤗 @ClementDelangue
91K Followers 5K Following Co-founder & CEO @HuggingFace 🤗, the open and collaborative platform for AI buildersNathan Benaich @nathanbenaich
51K Followers 32K Following solo member of investment staff @airstreet, brewing ambition @airstreetcafe, next token predictor @airstreetpressZhaoxi Chen @Frozen_Burning
502 Followers 336 Following Ph.D. student @MMLabNTU | Neural Rendering & 3D Generation | Ex Intern @RealityLabsZhang Junzhe @ZhangJunzhetom
94 Followers 202 Following PhD student @ S-Lab, Nanyang Technological University; Algorithm Researcher @ SensetimeFramer 🇱🇹 @0xFramer
13K Followers 1K Following I create beautiful animations using AI 🎬 Follow me to learn it 🧙 Enroll in AI Animation course: https://t.co/Qgn2d4sAvOMartin Nebelong @MartinNebelong
27K Followers 1K Following 🎨 Artist on the forefront of tech, VR and AI. Client list include Runway, Lumalabs, Media Molecule, The UN, LEGO, Adobe. Once performed VR for 40k audience.Ying Shan @yshan2u
1K Followers 576 Following Distinguished Scientist @TencentGlobal, Founder of PCG ARC Lab, Director of AI Lab Visual Computing. Formerly @Microsoft, @MSFTResearch. Views are my own.Yang Song @DrYangSong
10K Followers 887 Following Leading the Strategic Explorations team @OpenAI. Score-Based Models. Diffusion Models. Consistency Models.Chenlin Meng @chenlin_meng
8K Followers 833 Following Co-founder & CTO @pika_labs | ex @StanfordAILab @StanfordXiQiao 西乔 @recatm
140K Followers 3K Following Digital Artist, Illustrator & Cartoonist | Founder of https://t.co/M44KNgvLie | DreamLens Author of book «Illustrated History of Programming»Max @maxescu
12K Followers 514 Following On a mission to create a full-length movie entirely with AI. Follow to see it happen in real-time. #Runway Creative Partner#CVPR2024 @CVPR
41K Followers 329 Following Official account for IEEE/CVF Conference on Computer Vision & Pattern Recognition. #CVPR2024 🇺🇸 hosts @CSProfKGD @abby621 @jbhuang0604 @hi_ice_boy @BoqingGoPlaying around with @WonderDynamics Kinda crazy what's possible with it. Skater: Gustavo Ribeiro
Woah, this worked so much better than I expected
IDM-VTON: Improving Diffusion Models for Authentic Virtual Try-on in the Wild @impriansh got this🔥 model up & running Try it out on @replicate👇
Video2Game can convert videos of real-world scenes into realistic and interactive game environments! Always wanted this as a kid 🤯 Links ⬇️
⚡ A kind of 3D brush Tiny Glade is going to be just a relaxing castle doodling game. No more, no less. More than enough! 💕 The game seems amazing. But oh my god... Think about what could be done by further abstracting the idea of that "3D brush."
SAM + Optical Flow = FlowSAM FlowSAM can discover and segment moving objects in a video and outperforms all previous approaches by a considerable margin in both single and multi-object benchmarks 🔥 robots.ox.ac.uk/~vgg/research/…
Thanks @_akhaliq for promoting our work! Our PhysDreamer synthesizes physically-interactable 3D objects. Play with your favorite soft objects🌹🪴🌿. Project website: physdreamer.github.io
PhysDreamer Physics-Based Interaction with 3D Objects via Video Generation Realistic object interactions are crucial for creating immersive virtual experiences, yet synthesizing realistic 3D object dynamics in response to novel interactions remains a significant
🤯 This is insane Simulon can add any 3D model to your real footage video in a matter of minutes. It's so real that I almost can touch it!
Unlock long #video generation at a lower cost with keyframe generation and #InstantSplat! 📸Leveraging 12 key frames from the #Sora video (#Santorini ), we perform pose-free 3D modeling with InstantSplat. ⚡️Training in 40 seconds with an #A100 GPU. ✍️Efficient rendering of…
Adobe presents VideoGigaGAN! A new video upscaling model that can upsample a video up to 8x with rich details. 10 wild examples ⬇️
Learning H-Infinity Locomotion Control Stable locomotion in precipitous environments is an essential capability of quadruped robots, demanding the ability to resist various external disturbances. However, recent learning-based policies only use basic domain randomization to
Thanks to @_akhaliq for sharing! Check out SEED-X, your virtual assistant, the latest in our SEED series. It's a multimodal foundation model designed for real-world tasks (see attached images) that unifies understanding and generation. 🤩 Project page: github.com/AILab-CVC/SEED…
SEED-X Multimodal Models with Unified Multi-granularity Comprehension and Generation The rapid evolution of multimodal foundation model has demonstrated significant progresses in vision-language understanding and generation, e.g., our previous work SEED-LLaMA. However,
Thanks @_akhaliq . Excited to share our MeshLRM! This novel sparse-view 3D LRM produces high-quality mesh assets in < 1 second, featuring a simpler architecture and delivering better visual quality than our previous NeRF LRMs. Check out more results on sarahweiii.github.io/meshlrm/
MeshLRM Large Reconstruction Model for High-Quality Mesh We propose MeshLRM, a novel LRM-based approach that can reconstruct a high-quality mesh from merely four input images in less than one second. Different from previous large reconstruction models (LRMs) that focus on
Check our MeshLRM work for fast sparse-view mesh reconstruction! We showed the power of decoder-only transformer and context expansion (similar to LLMs), and diff. marching cubes! Great collaboration between UCSD (@SarahWeii, @haosu_twitr ) and Adobe Research!
MeshLRM Large Reconstruction Model for High-Quality Mesh We propose MeshLRM, a novel LRM-based approach that can reconstruct a high-quality mesh from merely four input images in less than one second. Different from previous large reconstruction models (LRMs) that focus on
📢VBench now Supports I2V Eval📢 📊#VBench now supports the multi-dimensional evaluation of Image-to-Video (I2V) models 🏆#DynamiCrafter and #SVD are among the top models - Code: github.com/Vchitect/VBench - Leaderboard @huggingface: huggingface.co/spaces/Vchitec… . Thanks to @_akhaliq!
VBench demo: huggingface.co/spaces/Vchitec… paper page: huggingface.co/papers/2311.17… Comprehensive Benchmark Suite for Video Generative Models
📢📢 Align Your Steps: Optimizing Sampling Schedules in Diffusion Models research.nvidia.com/labs/toronto-a… TL;DR: We introduce a method for obtaining improved sampling schedules for diffusion models, resulting in better samples at the same computation cost. (1/5)
So excited that our 𝗗𝘆𝗻𝗮𝗺𝗶𝗖𝗿𝗮𝗳𝘁𝗲𝗿-𝟭𝟬𝟮𝟰 ranks 𝟭𝘀𝘁 on the I2V benchmark list from VBench!
VBench update: We support evaluating Image-to-Video (I2V) models at 𝗩𝗕𝗲𝗻𝗰𝗵-𝗜𝟮𝗩 🖼️ Image Suite: multi-scale, multi-aspect-ratio, comprehensive content variety 📏 Dimensions: video-image consistency, camera motion, video quality, etc. 👨💻 Code: github.com/Vchitect/VBench
Thanks @_akhaliq , @liuziwei7! Glad to see our I2V DynamiCrafter at Top1, and t2V VideoCrafter2 at Top3 on your VBench leaderboard.
📢VBench now Supports I2V Eval📢 📊#VBench now supports the multi-dimensional evaluation of Image-to-Video (I2V) models 🏆#DynamiCrafter and #SVD are among the top models - Code: github.com/Vchitect/VBench - Leaderboard @huggingface: huggingface.co/spaces/Vchitec… . Thanks to @_akhaliq!