Sida Peng
@pengsida
Followers
717
Following
844
Media
3
Statuses
31
Happy to share our CVPR'25 work: Elevating metric depth estimation for large-scale scenes 👀.Code: Project Page:
0
30
202
RT @pablovelagomez1: Recently, I've been playing with my iPhone ToF sensor, but the problem has always been the abysmal resolution (256x192….
0
219
0
RT @XingyiHe1: Excited to share our work MatchAnything:.We pre-train strong universal image matching models that exhibit remarkable general….
0
162
0
RT @realzhenxu: Tired of short multi-view video datasets?.Check out our new SelfCap dataset with up to 10 minutes of 24-cameras high-qualit….
0
29
0
Check out our work on transforming Depth Anything into an excellent metric depth estimator.
Want to use Depth Anything, but need metric depth rather than relative depth?. Thrilled to introduce Prompt Depth Anything, a new paradigm for accurate metric depth estimation with up to 4K resolution. 👉Key Message: Depth foundation models like DA have already internalized rich
1
4
65
The length is crucial for immersive videos. We have elevated the duration from seconds to minutes, progressing towards practical volumetric video experiences.
Tired of short volumetric videos that only last a few seconds? Checkout our new SIGGRAPH Asia paper:.Representing Long Volumetric Video with Temporal Gaussian Hierarchy.A new way to model minutes or even longer volumetric videos!
0
1
33
Excited to share our SIGGRAPH Asia 2024 paper GVHMR 🥳. We can accurately estimates human motions in the world coordinate system, which are readily transferred to the simulator. Code: HuggingFace demo:
9
67
421
RT @YuxiXiaohenry: @skalskip92 Thank you for your generous compliment. Code and checkpoint are released here:.We al….
0
1
0
RT @YuxiXiaohenry: Code of Spatracker is released! Try to explore tracking pixels in 3D via 👉 .Below are several 3D….
0
65
0
RT @realzhenxu: (1/8) Ever wanted to create an avatar of yourself that interacts realistically with different lighting?. In our CVPR 2024 H….
0
24
0