Deqing Sun

43

Papers

268

Total Citations

Papers (43)

Probing the 3D Awareness of Visual Foundation Models

ZeroNVS: Zero-Shot 360-Degree View Synthesis from a Single Image

SMooDi: Stylized Motion Diffusion Model

SHINOBI: Shape and Illumination using Neural Object Decomposition via BRDF Optimization In-the-wild

One-Shot Open Affordance Learning with Foundation Models

WonderJourney: Going from Anywhere to Everywhere

GALA3D: Towards Text-to-3D Complex Scene Generation via Layout-guided Generative Gaussian Splatting

Layered RGBD Scene Flow Estimation

Blind Image Deblurring Using Dark Channel Prior

Optical Flow With Semantic Segmentation and Localized Layers

Learning Superpixels With Segmentation-Aware Affinity Loss

SPLATNet: Sparse Lattice Networks for Point Cloud Processing

Learning Dual Convolutional Neural Networks for Low-Level Vision

PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume

Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation

Pixel-Adaptive Convolutional Neural Networks

Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation

LASR: Learning Articulated Shape Reconstruction From a Monocular Video

Adaptive Prototype Learning and Allocation for Few-Shot Segmentation

HumanGPS: Geodesic PreServing Feature for Dense Human Correspondences

AutoFlow: Learning a Better Training Set for Optical Flow

Pyramid Adversarial Training Improves ViT Performance

Kubric: A Scalable Dataset Generator

Accidental Light Probes

LOCATE: Localize and Transfer Object Parts for Weakly Supervised Affordance Grounding

Self-Supervised AutoFlow

Learning to Super-Resolve Blurry Face and Text Images

Unsupervised Video Interpolation Using Cycle Consistency

Motion Prompting: Controlling Video Generation with Motion Trajectories

SAMPLING: Scene-adaptive Hierarchical Multiplane Images Representation for Novel View Synthesis from a Single Image

VQ3D: Learning a 3D-Aware Generative Model on ImageNet

Learnable Cost Volume Using the Cayley Representation

FILM: Frame Interpolation for Large Motion

Adaptive Transformers for Robust Few-Shot Cross-Domain Face Anti-Spoofing

Disentangling Architecture and Training for Optical Flow

SENSE: A Shared Encoder Network for Scene-Flow Estimation

High-Resolution Frame Interpolation with Patch-based Cascaded Diffusion

DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes

Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence

ViSER: Video-Specific Surface Embeddings for Articulated 3D Shape Reconstruction

SAMURAI: Shape And Material from Unconstrained Real-world Arbitrary Image collections

The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation

A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence