Min Sun

papers

1,718

total citations

papers (25)

Direct Voxel Grid Optimization: Super-Fast Convergence for Radiance Fields Reconstruction

CVPR 2022arXiv

1,283

citations

ImGeoNet: Image-induced Geometry-aware Voxel Representation for Multi-view 3D Object Detection

ICCV 2023arXiv

citations

Specialize and Fuse: Pyramidal Output Representation for Semantic Segmentation

ICCV 2021arXiv

citations

GenRC: Generative 3D Room Completion from Sparse Image Collections

ECCV 2024arXiv

citations

360-MLC: Multi-view Layout Consistency for Self-training and Hyper-parameter Tuning

NEURIPS 2022arXiv

citations

POp-GS: Next Best View in 3D-Gaussian Splatting with P-Optimality

CVPR 2025arXiv

citations

No More Ambiguity in 360° Room Layout via Bi-Layout Estimation

CVPR 2024arXiv

citations

Zero-shot 3D Question Answering via Voxel-based Dynamic Token Compression

CVPR 2025

citations

Correspondence-Free SE(3) Point Cloud Registration in RKHS via Unsupervised Equivariant Learning

ECCV 2024arXiv

citations

OpenM3D: Open Vocabulary Multi-view Indoor 3D Object Detection without Human Annotations

ICCV 2025arXiv

citations

Self-Training Room Layout via Geometry-aware Ray-casting

ECCV 2024

citations

UA-Pose: Uncertainty-Aware 6D Object Pose Estimation and Online Object Completion with Partial References

CVPR 2025arXiv

citations

Details Matter for Indoor Open-vocabulary 3D Instance Segmentation

ICCV 2025arXiv

citations

Bidirectional Alignment for Domain Adaptive Detection with Transformers

ICCV 2023

citations

Mitigating Forgetting in Online Continual Learning via Instance-Aware Parameterization

NEURIPS 2020

citations

LED2-Net: Monocular 360deg Layout Estimation via Differentiable Depth Rendering

CVPR 2021

citations

BiFuse: Monocular 360 Depth Estimation via Bi-Projection Fusion

CVPR 2020

citations

Min Sun

papers (25)

Direct Voxel Grid Optimization: Super-Fast Convergence for Radiance Fields Reconstruction

HoHoNet: 360 Indoor Holistic Understanding With Latent Horizontal Features

Semiconductor Defect Detection by Hybrid Classical-Quantum Deep Learning

Autoregressive 3D Shape Generation via Canonical Mapping

Learning 3D Dense Correspondence via Canonical Point Autoencoder

Controllable Image Synthesis via SegVAE

Indoor Panorama Planar 3D Reconstruction via Divide and Conquer

Data Efficient 3D Learner via Knowledge Transferred from 2D Model

GDA: Generalized Diffusion for Robust Test-time Adaptation

ImGeoNet: Image-induced Geometry-aware Voxel Representation for Multi-view 3D Object Detection

Specialize and Fuse: Pyramidal Output Representation for Semantic Segmentation

GenRC: Generative 3D Room Completion from Sparse Image Collections

360-MLC: Multi-view Layout Consistency for Self-training and Hyper-parameter Tuning

POp-GS: Next Best View in 3D-Gaussian Splatting with P-Optimality

No More Ambiguity in 360° Room Layout via Bi-Layout Estimation

Zero-shot 3D Question Answering via Voxel-based Dynamic Token Compression

Correspondence-Free SE(3) Point Cloud Registration in RKHS via Unsupervised Equivariant Learning

OpenM3D: Open Vocabulary Multi-view Indoor 3D Object Detection without Human Annotations

Self-Training Room Layout via Geometry-aware Ray-casting

UA-Pose: Uncertainty-Aware 6D Object Pose Estimation and Online Object Completion with Partial References

Details Matter for Indoor Open-vocabulary 3D Instance Segmentation

Bidirectional Alignment for Domain Adaptive Detection with Transformers

Mitigating Forgetting in Online Continual Learning via Instance-Aware Parameterization

LED2-Net: Monocular 360deg Layout Estimation via Differentiable Depth Rendering

BiFuse: Monocular 360 Depth Estimation via Bi-Projection Fusion

papers (25)

Direct Voxel Grid Optimization: Super-Fast Convergence for Radiance Fields Reconstruction

HoHoNet: 360 Indoor Holistic Understanding With Latent Horizontal Features

Semiconductor Defect Detection by Hybrid Classical-Quantum Deep Learning

Autoregressive 3D Shape Generation via Canonical Mapping

Learning 3D Dense Correspondence via Canonical Point Autoencoder

Controllable Image Synthesis via SegVAE

Indoor Panorama Planar 3D Reconstruction via Divide and Conquer

Data Efficient 3D Learner via Knowledge Transferred from 2D Model

GDA: Generalized Diffusion for Robust Test-time Adaptation

ImGeoNet: Image-induced Geometry-aware Voxel Representation for Multi-view 3D Object Detection

Specialize and Fuse: Pyramidal Output Representation for Semantic Segmentation

GenRC: Generative 3D Room Completion from Sparse Image Collections

360-MLC: Multi-view Layout Consistency for Self-training and Hyper-parameter Tuning

POp-GS: Next Best View in 3D-Gaussian Splatting with P-Optimality

No More Ambiguity in 360° Room Layout via Bi-Layout Estimation

Zero-shot 3D Question Answering via Voxel-based Dynamic Token Compression

Correspondence-Free SE(3) Point Cloud Registration in RKHS via Unsupervised Equivariant Learning

OpenM3D: Open Vocabulary Multi-view Indoor 3D Object Detection without Human Annotations

Self-Training Room Layout via Geometry-aware Ray-casting

UA-Pose: Uncertainty-Aware 6D Object Pose Estimation and Online Object Completion with Partial References

Details Matter for Indoor Open-vocabulary 3D Instance Segmentation

Bidirectional Alignment for Domain Adaptive Detection with Transformers

Mitigating Forgetting in Online Continual Learning via Instance-Aware Parameterization

LED2-Net: Monocular 360deg Layout Estimation via Differentiable Depth Rendering

BiFuse: Monocular 360 Depth Estimation via Bi-Projection Fusion