Oh by the way, I have embarked on a new adventure as a Research Scientist in Computer vision at @Simulon 🎉. I couldn't be more excited about the opportunities and challenges that lie ahead in making VFX available for everyone and empowering creators. Stay tuned!

RT @Almorgand: Look Ma, no markers Holistic performance capture without the hassle. TL;DR: hybrid approach from models trained exclusively….

RT @AnpeiC: 📢 Our new paper GaVS – 3D-Grounded Video Stabilization is out!. Key idea: feed-forward Dynamic Gaussian Splatting + test-time o….

Jiahao Ma 1,3, Lei Wang 2,3, @miaomiao_mm 1, David Ahmedt-Aristizabal 3, Chuong Nguyen 3. 1 Australian National University.2 Griffith University.3 @CSIRO 's Data61. Project page: Paper: Source code:

Puzzles: Unbounded Video-Depth Augmentation for Scalable End-to-End 3D Reconstruction. TL;DR: Puzzles augments 3D reconstruction training by generating diverse novel viewpoints and realistic camera trajectories from single images or video clips, eliminating redundant frames.

RT @MaxVOAO: I think I'll go back to basics

Zinuo You 1, @stam_g 2, @AnpeiC 1,3 @SiyuTang3 1, Dengxin Dai 2 . 1 @ETH.2 @Huawei Research Center, Zurich.3 University of Tübingen, Tübingen AI Center.

Project page: Paper: Source code: Dataset: Result collection:

GaVS: 3D-Grounded Video Stabilization via Temporally-Consistent Local Reconstruction and Rendering. TL;DR: Video stabilization task with feed-forward 3DGS reconstruction, ensuring robustness to diverse motions, full-frame rendering and high geometry consistency.

RT @pesarlin: We released COLMAP v3.12, which adds long-awaited end-to-end support for multi-camera rigs and 360° panoramas 👀 COLMAP just g….

@gene_ch0u 1,2, @wenqi_xian 1, @stevenygd 3, @mohsaied 2, @BharathHarihar3 2, @Jimantha 2, @realNingYu 1, @debfx 1. 1 @eyelinestudios / @netflix.2 @Cornell.3 @Stanford. Project page: Paper: Source code:

"FlashDepth: Real-time Streaming Video Depth Estimation at 2K Resolution". TL;DR: Depth estimation (2044×1148) streaming video at 24 FPS; careful modifications of pretrained single-image depth models, these capabilities are enabled with relatively little data and training.

Thank you @ychngji6 for sharing that paper!. Project page: Paper: Source code (MIT license!): Demo:

"Light of Normals: Unified Feature Representation for Universal Photometric Stereo". TL;DR: Achieve Up to 4K Resolution & 3D Scanner-Level Accurate Surface Normals Estimation; preserve high-frequency details via Wavelet Sampling

RT @ychngji6: Thrilled to unveil LINO - Light of Normals! 🌟 We Achieve Up to 4K Resolution & 3D Scanner-Level Accurate Surface Normals Esti….

RT @kali_shade: Hi all, I'm seeking freelance work involving shaders. I have +10 years of experience creating shader art and am available f….

@jiahaoshao1 1*, @YuanboYang60742 1*, Hongyu Zhou 1, Youmin Zhang 2,6, Yujun Shen 4, @vitorguizilini 5, @yuewang314 3, @mattpoggi 2, @yiyi_liao_ 1† .1 @ZJU_China 2 University of Bologna 3 University of Southern California 4 @AntGroup 5 @ToyotaResearch 6 Rock Universe AI.

Project page: Paper: Source code (MIT license): Hugging face demo:

"Learning Temporally Consistent Video Depth from Video Diffusion Priors". TL;DR: ChronoDepth addresses the challenge of streamed video depth estimation with video diffusion model.

RT @80Level: In case you missed it, check out @VfxGrace's rigged German Shepherd model, created entirely with Blender. Learn more and get….

@YuchenZhan54250 @Nik__V__ Chenwei Lyu Bhuvan Jhamb @yutianc @QiuYuhengQiu @JayKarhade Shreyas Jha @YaoyuHU @RamananDeva @smash0190 Wenshan Wang from @CarnegieMellon.