Jianming Zhang

55

Papers

243

Total Citations

Papers (55)

UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics

IMPRINT: Generative Object Compositing by Learning Identity-Preserving Representation

Unsupervised Video Object Segmentation with Joint Hotspot Tracking

Generative Image Layer Decomposition with Visual Effects

FINECAPTION: Compositional Image Captioning Focusing on Wherever You Want at Any Granularity

Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstruction

UniHuman: A Unified Model For Editing Human Images in the Wild

Refine-by-Align: Reference-Guided Artifacts Refinement through Semantic Alignment

Top-Down Visual Saliency Guided by Captions

Excitation Backprop for RNNs

Good View Hunting: Learning Photo Composition From Dense View Pairs

Neural Rejuvenation: Improving Deep Network Training by Enhancing Computational Resource Utilization

CapSal: Leveraging Captioning to Boost Semantics for Salient Object Detection

SDC-Depth: Semantic Divide-and-Conquer Network for Monocular Depth Estimation

Structure-Guided Ranking Loss for Single Image Depth Prediction

Learning Visual Emotion Representations From Web Data

SSN: Soft Shadow Network for Image Compositing

Mask Guided Matting via Progressive Refinement Network

Learning To Recover 3D Scene Shape From a Single Image

Multimodal Contrastive Training for Visual Representation Learning

Layered Depth Refinement With Mask Guidance

BokehMe: When Neural Rendering Meets Classical Rendering

Lite Vision Transformer With Enhanced Self-Attention

Single View Scene Scale Estimation Using Scale Field

Perspective Fields for Single Image Camera Calibration

3D Cinemagraphy From a Single Image

PixHt-Lab: Pixel Height Based Light Effect Generation for Image Compositing

LightPainter: Interactive Portrait Relighting With Freehand Scribble

SceneComposer: Any-Level Semantic Image Synthesis

ObjectStitch: Object Compositing With Diffusion Model

Minimum Barrier Salient Object Detection at 80 FPS

Fast Video Object Segmentation via Dynamic Targeting Network

Scaling Object Detection by Transferring Classification Weights

Towards High-Resolution Salient Object Detection

SSH: A Self-Supervised Framework for Image Harmonization

MetaShadow: Object-Centered Shadow Detection, Removal, and Synthesis

GAIT: Generating Aesthetic Indoor Tours with Deep Reinforcement Learning

Lens Parameter Estimation for Realistic Depth of Field Modeling

CLIFFNet for Monocular Depth Estimation with Hierarchical Embedding Loss

Open-Edit: Open-Domain Image Manipulation with Open-Vocabulary Instructions

Shape Adaptor: A Learnable Resizing Module

High-Resolution Image Inpainting with Iterative Confidence Feedback and Guided Upsampling

MPIB: An MPI-Based Bokeh Rendering Framework for Realistic Partial Occlusion Effects

Image Inpainting with Cascaded Modulation GAN and Object-Aware Training

Controllable Shadow Generation Using Pixel Height Maps

Neural Video Depth Stabilizer

Floating No More: Object-Ground Reconstruction from a Single Image

Amodal Scene Analysis via Holistic Occlusion Relation Inference and Generative Mask Completion

Holo-Relighting: Controllable Volumetric Portrait Relighting from a Single Image

Relightful Harmonization: Lighting-aware Portrait Background Replacement

SmartMask: Context Aware High-Fidelity Mask Generation for Fine-grained Object Insertion and Layout Control

Salient Object Subitizing

Unconstrained Salient Object Detection via Proposal Subset Optimization

Sequence-to-Segment Networks for Segment Detection

PHOTOSWAP: Personalized Subject Swapping in Images