Baorui Ma
YOU?
Author Swipe
View article: NeRFPrior: Learning Neural Radiance Field as a Prior for Indoor Scene Reconstruction
NeRFPrior: Learning Neural Radiance Field as a Prior for Indoor Scene Reconstruction Open
Recently, it has shown that priors are vital for neural implicit functions to reconstruct high-quality surfaces from multi-view RGB images. However, current priors require large-scale pre-training, and merely provide geometric clues withou…
View article: You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale
You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale Open
Recent 3D generation models typically rely on limited-scale 3D `gold-labels' or 2D diffusion priors for 3D content creation. However, their performance is upper-bounded by constrained 3D priors due to the lack of scalable learning paradigm…
View article: Fast Learning of Signed Distance Functions from Noisy Point Clouds via Noise to Noise Mapping
Fast Learning of Signed Distance Functions from Noisy Point Clouds via Noise to Noise Mapping Open
Learning signed distance functions (SDFs) from point clouds is an important task in 3D computer vision. However, without ground truth signed distances, point normals or clean point clouds, current methods still struggle from learning SDFs …
View article: UDiFF: Generating Conditional Unsigned Distance Fields with Optimal Wavelet Diffusion
UDiFF: Generating Conditional Unsigned Distance Fields with Optimal Wavelet Diffusion Open
Diffusion models have shown remarkable results for image generation, editing and inpainting. Recent works explore diffusion models for 3D shape generation with neural implicit functions, i.e., signed distance function and occupancy functio…
View article: Learning Continuous Implicit Field with Local Distance Indicator for Arbitrary-Scale Point Cloud Upsampling
Learning Continuous Implicit Field with Local Distance Indicator for Arbitrary-Scale Point Cloud Upsampling Open
Point cloud upsampling aims to generate dense and uniformly distributed point sets from a sparse point cloud, which plays a critical role in 3D computer vision. Previous methods typically split a sparse point cloud into several local patch…
View article: Learning Continuous Implicit Field with Local Distance Indicator for Arbitrary-Scale Point Cloud Upsampling
Learning Continuous Implicit Field with Local Distance Indicator for Arbitrary-Scale Point Cloud Upsampling Open
Point cloud upsampling aims to generate dense and uniformly distributed point sets from a sparse point cloud, which plays a critical role in 3D computer vision. Previous methods typically split a sparse point cloud into several local patch…
View article: Differentiable Registration of Images and LiDAR Point Clouds with VoxelPoint-to-Pixel Matching
Differentiable Registration of Images and LiDAR Point Clouds with VoxelPoint-to-Pixel Matching Open
Cross-modality registration between 2D images from cameras and 3D point clouds from LiDARs is a crucial task in computer vision and robotic. Previous methods estimate 2D-3D correspondences by matching point and pixel patterns learned by ne…
View article: GeoDream: Disentangling 2D and Geometric Priors for High-Fidelity and Consistent 3D Generation
GeoDream: Disentangling 2D and Geometric Priors for High-Fidelity and Consistent 3D Generation Open
Text-to-3D generation by distilling pretrained large-scale text-to-image diffusion models has shown great promise but still suffers from inconsistent 3D geometric structures (Janus problems) and severe artifacts. The aforementioned problem…
View article: Uni3D: Exploring Unified 3D Representation at Scale
Uni3D: Exploring Unified 3D Representation at Scale Open
Scaling up representations for images or text has been extensively investigated in the past few years and has led to revolutions in learning vision and language. However, scalable representation for 3D objects and scenes is relatively unex…
View article: Learning a More Continuous Zero Level Set in Unsigned Distance Fields through Level Set Projection
Learning a More Continuous Zero Level Set in Unsigned Distance Fields through Level Set Projection Open
Latest methods represent shapes with open surfaces using unsigned distance functions (UDFs). They train neural networks to learn UDFs and reconstruct surfaces with the gradients around the zero level set of the UDF. However, the differenti…
View article: NeAF: Learning Neural Angle Fields for Point Normal Estimation
NeAF: Learning Neural Angle Fields for Point Normal Estimation Open
Normal estimation for unstructured point clouds is an important task in 3D computer vision. Current methods achieve encouraging results by mapping local patches to normal vectors or learning local surface fitting using neural networks. How…
View article: Learning Signed Distance Functions from Noisy 3D Point Clouds via Noise to Noise Mapping
Learning Signed Distance Functions from Noisy 3D Point Clouds via Noise to Noise Mapping Open
Learning signed distance functions (SDFs) from 3D point clouds is an important task in 3D computer vision. However, without ground truth signed distances, point normals or clean point clouds, current methods still struggle from learning SD…
View article: Towards Better Gradient Consistency for Neural Signed Distance Functions via Level Set Alignment
Towards Better Gradient Consistency for Neural Signed Distance Functions via Level Set Alignment Open
Neural signed distance functions (SDFs) have shown remarkable capability in representing geometry with details. However, without signed distance supervision, it is still a challenge to infer SDFs from point clouds or multi-view images usin…
View article: NeAF: Learning Neural Angle Fields for Point Normal Estimation
NeAF: Learning Neural Angle Fields for Point Normal Estimation Open
Normal estimation for unstructured point clouds is an important task in 3D computer vision. Current methods achieve encouraging results by mapping local patches to normal vectors or learning local surface fitting using neural networks. How…
View article: CAP-UDF: Learning Unsigned Distance Functions Progressively from Raw Point Clouds with Consistency-Aware Field Optimization
CAP-UDF: Learning Unsigned Distance Functions Progressively from Raw Point Clouds with Consistency-Aware Field Optimization Open
Surface reconstruction for point clouds is an important task in 3D computer vision. Most of the latest methods resolve this problem by learning signed distance functions from point clouds, which are limited to reconstructing closed surface…
View article: Surface Reconstruction from Point Clouds by Learning Predictive Context Priors
Surface Reconstruction from Point Clouds by Learning Predictive Context Priors Open
Surface reconstruction from point clouds is vital for 3D computer vision. State-of-the-art methods leverage large datasets to first learn local context priors that are represented as neural network-based signed distance functions (SDFs) wi…
View article: Reconstructing Surfaces for Sparse Point Clouds with On-Surface Priors
Reconstructing Surfaces for Sparse Point Clouds with On-Surface Priors Open
It is an important task to reconstruct surfaces from 3D point clouds. Current methods are able to reconstruct surfaces by learning Signed Distance Functions (SDFs) from single point clouds without ground truth signed distances or point nor…
View article: 3D-OAE: Occlusion Auto-Encoders for Self-Supervised Learning on Point Clouds
3D-OAE: Occlusion Auto-Encoders for Self-Supervised Learning on Point Clouds Open
The manual annotation for large-scale point clouds is still tedious and unavailable for many harsh real-world tasks. Self-supervised learning, which is used on raw and unlabeled data to pre-train deep neural networks, is a promising approa…
View article: Topical Delivery of Levocarnitine to the Cornea and Anterior Eye by Thermosensitive in-situ Gel for Dry Eye Disease
Topical Delivery of Levocarnitine to the Cornea and Anterior Eye by Thermosensitive in-situ Gel for Dry Eye Disease Open
The LCTG has a good curative effect on mice with DED, and the overall curative effect is better than that of levocarnitine solution.
View article: Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfaces
Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfaces Open
Reconstructing continuous surfaces from 3D point clouds is a fundamental operation in 3D geometry processing. Several recent state-of-the-art methods address this problem using neural networks to learn signed distance functions (SDFs). In …