Search Results for author:
Found 17 papers, 9 papers with code
Flash3D: Super-scaling Point Transformers through Joint Hardware-Geometry Locality
Recent efforts recognize the power of scale in 3D learning (e. g. PTv3) and attention mechanisms (e. g. FlashAttention).
VLM-AD: End-to-End Autonomous Driving through Vision-Language Model Supervision
Human drivers rely on commonsense reasoning to navigate diverse and dynamic real-world scenarios.
Uncertainty-Guided Enhancement on Driving Perception System via Foundation Models
Multimodal foundation models offer promising advancements for enhancing driving perception systems, but their high computational and financial costs pose challenges.
VLMine: Long-Tail Data Mining with Vision Language Models
We propose a simple and scalable data mining approach that leverages the knowledge contained within a large vision language model (VLM).
VLM-KD: Knowledge Distillation from VLM for Long-Tail Visual Recognition
To our knowledge, this work is the first to utilize knowledge distillation with text supervision generated by an off-the-shelf VLM and apply it to vanilla randomly initialized vision encoders.
The Role of Linguistic Priors in Measuring Compositional Generalization of Vision-Language Models
Compositionality is a common property in many modalities including natural languages and images, but the compositional generalization of multi-modal models is not well-understood.
LiDAR-Based 3D Object Detection via Hybrid 2D Semantic Scene Generation
Bird's-Eye View (BEV) features are popular intermediate scene representations shared by the 3D backbone and the detector head in LiDAR-based object detectors.
Implicit Surface Contrastive Clustering for LiDAR Point Clouds
The first task focuses on learning semantic information by sorting local groups of points in the scene into a globally consistent set of semantically meaningful clusters using contrastive learning.
HM3D-ABO: A Photo-realistic Dataset for Object-centric Multi-view 3D Reconstruction
Reconstructing 3D objects is an important computer vision task that has wide application in AR/VR.
FvOR: Robust Joint Shape and Pose Optimization for Few-view Object Reconstruction
In this paper, we present FvOR, a learning-based object reconstruction method that predicts accurate 3D models given a few images with noisy input poses.
Scene Synthesis via Uncertainty-Driven Attribute Synchronization
This task is challenging because 3D scenes exhibit diverse patterns, ranging from continuous ones, such as object sizes and the relative poses between pairs of shapes, to discrete patterns, such as occurrence and co-occurrence of objects with symmetrical relationships.
ARAPReg: An As-Rigid-As Possible Regularization Loss for Learning Deformable Shape Generators
Our approach builds on an approximation of the as-rigid-as possible (or ARAP) deformation energy.
Self-Supervised Pretraining of 3D Features on any Point-Cloud
Pretraining on large labeled datasets is a prerequisite to achieve good performance in many computer vision tasks like 2D object recognition, video classification etc.
H3DNet: 3D Object Detection Using Hybrid Geometric Primitives
We show how to convert the predicted geometric primitives into object proposals by defining a distance function between an object and the geometric primitives.
Ranked #3 on
3D Object Detection
on ARKitScenes
Joint Learning of Neural Networks via Iterative Reweighted Least Squares
We formulate this problem as joint learning of multiple copies of the same network architecture and enforce the network weights to be shared across these networks.
Path-Invariant Map Networks
Optimizing a network of maps among a collection of objects/domains (or map synchronization) is a central problem across computer vision and many other relevant fields.
Deep Generative Modeling for Scene Synthesis via Hybrid Representations
We show a principled way to train this model by combining discriminator losses for both a 3D object arrangement representation and a 2D image-based representation.
