Jing He

@Jingheya

PhD Student @HKUST (guangzhou); Research Intern @Kling_ai.

jingheya.github.io

Joined November 2023

Following

163

Followers

Replies Reposts Media

Jing He
@Jingheya
Mar 14
Thanks for sharing, @_akhaliq ! Feel free to check out our new SoTA video depth estimator.🥳🤗👏💪 Useful links ⬇️ Demo: huggingface.co/spaces/haodong… Code: github.com/EnVision-Resea… Paper: arxiv.org/abs/2603.12250 Page: dvd-project.github.io
AK
@_akhaliq
Mar 13
DVD Deterministic Video Depth Estimation with Generative Priors paper: huggingface.co/papers/2603.12…
00:00
3
Jing He
@Jingheya
Jan 26
insane!!!
Haven Feng
@HavenFeng
Jan 23
✨Thinking with Blender~ Meet VIGA: a multimodal agent that autonomously codes 3D/4D blender scenes from any image, with no human, no training! @berkeley_ai #LLMs #Blender #Agent 🧵1/6
00:00
Jing He
@Jingheya
Dec 23, 2025
Thanks @_akhaliq for sharing our work! 🤗Our StereoPilot is an efficient feed-forward architecture that leverages pre-trained video diffusion priors to directly synthesize novel views for stereo conversion. 🥳 Page: hit-perfect.github.io/StereoPilot/
AK
@_akhaliq
Dec 20, 2025
StereoPilot Learning Unified and Efficient Stereo Conversion via Generative Priors
00:00
Jing He
@Jingheya
Dec 2, 2025
Thanks @_akhaliq for sharing our work!!!🌹 Lotus-2 effectively analyzes the DiT-based rectified-flow formulation and leverages the pre-trained generative model as a deterministic world prior, achieving SoTA performance with significantly finer details.🥳
AK
@_akhaliq
Dec 2, 2025
Lotus-2 Advancing Geometric Dense Prediction with Powerful Image Generative Model
1
Jing He
@Jingheya
Oct 1, 2025
Sharing our new panoramic depth estimation method!🥰🤗🥳 It delivers remarkable geometric fidelity and exceptional zero-shot generalization!🤩
AK
@_akhaliq
Oct 1, 2025
DA^2 Depth Anything in Any Direction
00:00