Deqing Sun
- Papers
- 12
Cite
Notes
Only stored in your browser.
Authored papers
12LiteFrame: Efficient Vision Encoders Unlock Frame Scaling in Video LLMs
arXiv 2026
LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory
arXiv 2026
Force Prompting: Video Generation Models Can Learn and Generalize Physics-based Control Signals
arXiv 2025
MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion
arXiv 2024
Probing the 3D Awareness of Visual Foundation Models
CVPR 2024 1
OmniControl: Control Any Joint at Any Time for Human Motion Generation
arXiv 2023
A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence
NeurIPS 2023 11
Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence
CVPR 2024 1
ZeroNVS: Zero-Shot 360-Degree View Synthesis from a Single Image
CVPR 2024 1
FILM: Frame Interpolation for Large Motion
arXiv 2022
Kubric: A scalable dataset generator
CVPR 2022 1
An Extendable, Efficient and Effective Transformer-based Object Detector
arXiv 2022
Affiliations
Frequent co-authors
10from 12 papers