Tianfan Xue

28

Papers

3,202

Total Citations

Papers (28)

Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling

NeurIPS 2016arXiv

MarrNet: 3D Shape Reconstruction via 2.5D Sketches

NeurIPS 2017arXiv

Visual Dynamics: Probabilistic Future Frame Synthesis via Cross Convolutional Networks

NeurIPS 2016arXiv

AutoDIR: Automatic All-in-One Image Restoration with Latent Diffusion

Teaching Large Language Models to Regress Accurate Image Quality Scores Using Score Distribution

GenNBV: Generalizable Next-Best-View Policy for Active 3D Reconstruction

Text-to-3D Generation with Bidirectional Diffusion using both 2D and 3D priors

Interactive3D: Create What You Want by Interactive 3D Generation

From One to More: Contextual Part Latents for 3D Generation

UltraFusion: Ultra High Dynamic Imaging using Exposure Fusion

NVComposer: Boosting Generative Novel View Synthesis with Multiple Sparse and Unposed Images

Multi-identity Human Image Animation with Structural Video Diffusion

PolarFree: Polarization-based Reflection-Free Imaging

HDRFlow: Real-Time HDR Video Reconstruction with Large Motions

AdaptiveAE: An Adaptive Exposure Strategy for HDR Capturing in Dynamic Scenes

Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling

Unprocessing Images for Learned Raw Denoising

AligNeRF: High-Fidelity Neural Radiance Fields via Alignment-Aware Training

How To Train Neural Networks for Flare Removal

Defocus Map Estimation and Deblurring From a Single Dual-Pixel Image

Joint Bilateral Learning for Real-time Universal Photorealistic Style Transfer

Fast and High Quality Image Denoising via Malleable Convolution

A Physics-Informed Blur Learning Framework for Imaging Systems

The Aperture Problem for Refractive Motion

From Gallery to Wrist: Realistic 3D Bracelet Insertion in Videos

GLEAM: Learning Generalizable Exploration Policy for Active Mapping in Complex 3D Indoor Scene

Token-Efficient VLM: High-Resolution Image Understanding via Dynamic Region Proposal

EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI