Anpei Chen
@AnpeiC
Followers
583
Following
157
Media
7
Statuses
39
Postdoc at the University of Tuebingen @AutoVisionGroup and ETH Zurich @ETH_en
Tuebingen
Joined April 2021
π» ππ
π½πΉπΌπΏπ² πΌππΏ π₯π²πππΉππ & ππΌπ±π² .β’ Demos & videos: .β’ Preprint on arXiv:
0
0
5
π’ Our new paper GaVS β 3D-Grounded Video Stabilization is out!. Key idea: feed-forward Dynamic Gaussian Splatting + test-time optimization. Robust, consistent, and cropping-free πΉ. π₯ Project: @youzn99 @stam_g @SiyuTang3 Dengxin Dai.#SIGGRAPH25 #3DGS
4
25
191
Feature up up up πΌοΈβ¨. We tackle the resolution bottleneck of Vision Foundation Models (like DINOv2 & CLIP) with a coordinate-based cross-attention upsampler. Plug and play β stronger, faster than ever! π. #VisionModels #DeepLearning #ComputerVision.
Introducing LoftUp!. A stronger (than ever) and lightweight feature upsampler for vision encoders that can boost performance on dense prediction tasks by 20%β100%!. Easy to plug into models like DINOv2, CLIP, SigLIP β simple design, big gains. Try it out!.
1
4
56
Main contributions:. π₯ Reconstruction-driven video diffusion model.π Cyclical fusion of reconstruction and generation.π New benchmark for NVS: Masked View Synthesis
0
0
0
Too many artifacts for GS reconstruction? Please checkout GenFusion: Closing the Loop between Reconstruction and Generation via Videos. π Project page: π» Code: #3D #DiffusionModels #ViewSynthesis #GenFusion #CVPR2025
3
38
195
Why train when you can adapt? Easi3R unlocks training-free motion estimation from DUSt3R using attention adaptationβno fine-tuning needed! π‘.
π¦£Easi3R: 4D Reconstruction Without Training!. Limited 4D datasets? Take it easy. #Easi3R adapts #DUSt3R for 4D reconstruction by disentangling and repurposing its attention maps β make 4D reconstruction easier than ever!. πPage:
1
17
100
RT @faneggchen: How much 3D do visual foundation models (VFMs) know?. Previous work requires 3D data for probing β expensive to collect!. #β¦.
0
33
0
RT @angelaqdai: How can we generate high-fidelity, complex 3D scenes?. @QTDSMQ's LT3SD decomposes 3D scenes into latent tree representationβ¦.
0
78
0
RT @3DVconf: #3DV2025AMA very first guest, Michael J. Black from MPI-IS & Meshcapade @Michael_J_Black! π. π You have now 24 HOURS to ask hiβ¦.
0
7
0
Struggling to secure more GPUs for training large X (reconstruction, Gaussian, etc) models? Check out LaRa, a lightweight 3D vision model designed to efficiently handle large-baseline reconstruction challenges.
1
11
128
Welcome to NRI, see you tomorrow at 1:30pm.
The Neural Rendering workshop will take place at #CVPR2024 in Seattle! .@CVPR. Organized by @fnzhan0507 @AnpeiC @AdamKortylewski @_atewari @SiyuTang3 Christian Theobalt. We have a fantastic speaker line-up!
0
2
15
RT @DeemosTech: πRodin Gen-1 is the largest 3D-native #GenerativeAI, which is same as #SD. Besides its ability to generate #3D model andβ¦.
0
120
0
RT @Besteuler: π Introducing GraphDreamer - A new framework to synthesize 3D scenes from scene graphs. GraphDreamer enables accurate 3D objβ¦.
0
24
0
RT @haosu_twitr: Our paper 'Single-Stage Diffusion NeRF' will be presented at #ICCV2023. We merge 3D diffusion with NeRF into a holistic moβ¦.
0
21
0
RT @jon_barron: Three years ago today, the project that eventually became NeRF started working (positional encoding was the missing piece tβ¦.
0
144
0