Search Results for author:
Found 28 papers, 14 papers with code
AlignMiF: Geometry-Aligned Multimodal Implicit Field for LiDAR-Camera Joint Synthesis
Through extensive experiments across various datasets and scenes, we demonstrate the effectiveness of our approach in facilitating better interaction between LiDAR and camera modalities within a unified neural field.
OpenSight: A Simple Open-Vocabulary Framework for LiDAR-Based Object Detection
OpenSight utilizes 2D-3D geometric priors for the initial discernment and localization of generic objects, followed by a more specific semantic interpretation of the detected objects.
BEVHeight++: Toward Robust Visual Centric 3D Object Detection
In essence, we regress the height to the ground to achieve a distance-agnostic formulation to ease the optimization process of camera-only perception methods.
FusionFormer: A Multi-sensory Fusion in Bird's-Eye-View and Temporal Consistent Transformer for 3D Object Detection
Multi-sensor modal fusion has demonstrated strong advantages in 3D object detection tasks.
Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training
In contrast, such privilege has not yet fully benefited 3D deep learning, mainly due to the limited availability of large-scale 3D datasets.
Ranked #3 on
3D Semantic Segmentation
on SemanticKITTI
(val mIoU metric, using extra
training data)
BEVControl: Accurately Controlling Street-view Elements with Multi-perspective Consistency via BEV Sketch Layout
To this end, we propose a two-stage generative method, dubbed BEVControl, that can generate accurate foreground and background contents.
FusionAD: Multi-modality Fusion for Prediction and Planning Tasks of Autonomous Driving
Building a multi-modality multi-task neural network toward accurate and robust performance is a de-facto standard in perception task of autonomous driving.
Dyn-E: Local Appearance Editing of Dynamic Neural Radiance Fields
We extensively evaluate our approach on various scenes and show that our approach achieves spatially and temporally consistent editing results.
LiDAR-NeRF: Novel LiDAR View Synthesis via Neural Radiance Fields
We address this challenge by formulating, to the best of our knowledge, the first differentiable end-to-end LiDAR rendering framework, LiDAR-NeRF, leveraging a neural radiance field (NeRF) to facilitate the joint learning of geometry and the attributes of 3D points.
BEVHeight: A Robust Framework for Vision-based Roadside 3D Object Detection
In essence, instead of predicting the pixel-wise depth, we regress the height to the ground to achieve a distance-agnostic formulation to ease the optimization process of camera-only perception methods.
Ranked #3 on
3D Object Detection
on Rope3D
Painting 3D Nature in 2D: View Synthesis of Natural Scenes from a Single Semantic Mask
We introduce a novel approach that takes a single semantic mask as input to synthesize multi-view consistent color images of natural scenes, trained with a collection of single images from the Internet.
$α$ DARTS Once More: Enhancing Differentiable Architecture Search by Masked Image Modeling
Differentiable architecture search (DARTS) has been a mainstream direction in automatic machine learning.
Ranked #10 on
Neural Architecture Search
on NAS-Bench-201, CIFAR-100
Learning Self-Regularized Adversarial Views for Self-Supervised Vision Transformers
Despite the success, its development and application on self-supervised vision transformers have been hindered by several barriers, including the high search cost, the lack of supervision, and the unsuitable search space.
Benchmarking the Robustness of LiDAR-Camera Fusion for 3D Object Detection
There are two critical sensors for 3D perception in autonomous driving, the camera and the LiDAR.
BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework
Fusing the camera and LiDAR information has become a de-facto standard for 3D object detection tasks.
Knowledge Distillation via the Target-aware Transformer
To this end, we propose a novel one-to-all spatial matching knowledge distillation approach.
NAS-Bench-Suite: NAS Evaluation is (Now) Surprisingly Easy
The release of tabular benchmarks, such as NAS-Bench-101 and NAS-Bench-201, has significantly lowered the computational overhead for conducting scientific research in neural architecture search (NAS).
An Analysis of Super-Net Heuristics in Weight-Sharing NAS
Weight sharing promises to make neural architecture search (NAS) tractable even on commodity hardware.
Landmark Regularization: Ranking Guided Super-Net Training in Neural Architecture Search
Weight sharing has become a de facto standard in neural architecture search because it enables the search to be done on commodity hardware.
Pyramid Architecture Search for Real-Time Image Deblurring
Multi-scale and multi-patch deep models have been shown effective in removing blurs of dynamic scenes.
How to Train Your Super-Net: An Analysis of Training Heuristics in Weight-Sharing NAS
Weight sharing promises to make neural architecture search (NAS) tractable even on commodity hardware.
Recurrent U-Net for Resource-Constrained Segmentation
State-of-the-art segmentation methods rely on very deep networks that are not always easy to train without very large training datasets and tend to be relatively slow to run on standard GPUs.
Overcoming Multi-Model Forgetting
We identify a phenomenon, which we refer to as multi-model forgetting, that occurs when sequentially training multiple deep networks with partially-shared parameters; the performance of previously-trained models degrades as one optimizes a subsequent one, due to the overwriting of shared parameters.
Evaluating the Search Phase of Neural Architecture Search
Neural Architecture Search (NAS) aims to facilitate the design of deep networks for new tasks.
Beyond One Glance: Gated Recurrent Architecture for Hand Segmentation
As evidenced by our results on standard hand segmentation benchmarks and on our own dataset, our approach outperforms these other, simpler recurrent segmentation techniques, as well as the state-of-the-art hand segmentation one.
Statistically-motivated Second-order Pooling
We then propose to make use of a square-root normalization, which makes the distribution of the resulting representation converge to a Gaussian, with which most classifiers of recent first-order networks complying.
Statistically Motivated Second Order Pooling
Our approach is motivated by a statistical analysis of the network's activations, relying on operations that lead to a Gaussian-distributed final representation, as inherently used by first-order deep networks.
Second-order Convolutional Neural Networks
By performing linear combinations and element-wise nonlinear operations, these networks can be thought of as extracting solely first-order information from an input image.
