Search Results for author:
Found 53 papers, 26 papers with code
Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility
The substantial training cost of diffusion models hinders their deployment.
Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation
In this paper, we propose SVG2, a training-free framework that maximizes identification accuracy and minimizes computation waste, achieving a Pareto frontier trade-off between generation quality and efficiency.
LDGNet: A Lightweight Difference Guiding Network for Remote Sensing Change Detection
First, to enhance the feature representation capability of the lightweight backbone network, we propose the Difference Guiding Module (DGM), which leverages multi-scale features extracted from the absolute difference image to progressively influence the original image encoder at each layer, thereby reinforcing feature extraction.
FlowKV: A Disaggregated Inference Framework with Low-Latency KV Cache Transfer and Load-Aware Scheduling
In this paper, we propose FlowKV, a novel disaggregated inference framework, which reduces the average transmission latency of KV cache by 96%, from 0. 944s to 0. 053s, almost eliminating the transfer time relative to the total request latency by optimizing the KV cache transfer.
Segment Any Motion in Videos
Moving object segmentation is a crucial task for achieving a high-level understanding of visual scenes and has numerous downstream applications.
Residual Policy Gradient: A Reward View of KL-regularized Objective
Building on this, we introduce Residual Policy Gradient (RPG), which extends RQL to policy gradient methods, allowing policy customization in gradient-based RL settings.
Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity
Diffusion Transformers (DiTs) dominate video generation but their high computational cost severely limits real-world applicability, usually requiring tens of minutes to generate a few seconds of video even on high-performance GPUs.
Bridging Viewpoint Gaps: Geometric Reasoning Boosts Semantic Correspondence
Finding semantic correspondences between images is a challenging problem in computer vision, particularly under significant viewpoint changes.
Maximizing Alignment with Minimal Feedback: Efficiently Learning Rewards for Visuomotor Robot Policy Alignment
While reinforcement learning from human feedback (RLHF) has become the predominant mechanism for alignment in non-embodied domains like large language models, it has not seen the same success in aligning visuomotor policies due to the prohibitive amount of human feedback required to learn visual reward functions.
A Lesson in Splats: Teacher-Guided Diffusion for 3D Gaussian Splats Generation with 2D Supervision
Additionally, our method is flexible, as it can learn from various 3D Gaussian Splat (3DGS) teachers with minimal adaptation; we demonstrate this by surpassing the performance of two different deterministic models as teachers, highlighting the potential generalizability of our framework.
DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenes
We present DeSiRe-GS, a self-supervised gaussian splatting representation, enabling effective static-dynamic decomposition and high-fidelity surface reconstruction in complex driving scenarios.
X-Drive: Cross-modality consistent multi-sensor data synthesis for driving scenarios
Recent advancements have exploited diffusion models for the synthesis of either LiDAR point clouds or camera image data in driving scenarios.
CompGS: Unleashing 2D Compositionality for Compositional Text-to-3D via Dynamically Optimizing 3D Gaussians
To achieve this goal, two core designs are proposed: (1) 3D Gaussians Initialization with 2D compositionality: We transfer the well-established 2D compositionality to initialize the Gaussian parameters on an entity-by-entity basis, ensuring both consistent 3D priors for each entity and reasonable interactions among multiple entities; (2) Dynamic Optimization: We propose a dynamic strategy to optimize 3D Gaussians using Score Distillation Sampling (SDS) loss.
CVT-Occ: Cost Volume Temporal Fusion for 3D Occupancy Prediction
Vision-based 3D occupancy prediction is significantly challenged by the inherent limitations of monocular vision in depth estimation.
TrajSSL: Trajectory-Enhanced Semi-Supervised 3D Object Detection
Semi-supervised 3D object detection is a common strategy employed to circumvent the challenge of manually labeling large-scale autonomous driving perception datasets.
DSLO: Deep Sequence LiDAR Odometry Based on Inconsistent Spatio-temporal Propagation
It consists of a pyramid structure with a spatial information reuse strategy, a sequential pose initialization module, a gated hierarchical pose refinement module, and a temporal feature propagation module.
Law of Vision Representation in MLLMs
We present the "Law of Vision Representation" in multimodal large language models (MLLMs).
CooPre: Cooperative Pretraining for V2X Cooperative Perception
Existing Vehicle-to-Everything (V2X) cooperative perception methods rely on accurate multi-agent 3D annotations.
Sparse Refinement for Efficient High-Resolution Semantic Segmentation
Finally, it leverages a gated ensembler to apply these sparse refinements to the initial coarse predictions.
Sparse Diffusion Policy: A Sparse, Reusable, and Flexible Policy for Robot Learning
The increasing complexity of tasks in robotics demands efficient strategies for multitask and continual learning.
Immiscible Diffusion: Accelerating Diffusion Training with Noise Assignment
Drawing inspiration from the immiscibility phenomenon in physics, we propose Immiscible Diffusion, a simple and effective method to improve the random mixture of noise-data mapping.
Zero-to-Hero: Enhancing Zero-Shot Novel View Synthesis via Attention Map Filtering
Additionally, we demonstrate the general applicability and effectiveness of Zero-to-Hero in multi-view, and image generation conditioned on semantic maps and pose.
Looking Backward: Streaming Video-to-Video Translation with Feature Banks
This paper introduces StreamV2V, a diffusion model that achieves real-time streaming video-to-video (V2V) translation with user prompts.
NeRF in Robotics: A Survey
Meticulous 3D environment representations have been a longstanding goal in computer vision and robotics fields.
Q-SLAM: Quadric Representations for Monocular SLAM
In this paper, we reimagine volumetric representations through the lens of quadrics.
StreamDiffusion: A Pipeline-level Solution for Real-time Interactive Generation
We introduce StreamDiffusion, a real-time diffusion pipeline designed for interactive image generation.
3DiffTection: 3D Object Detection with Geometry-Aware Diffusion Features
However, these features are initially trained on paired text and image data, which are not optimized for 3D tasks, and often exhibit a domain gap when applied to the target data.
What Matters to You? Towards Visual Representation Alignment for Robot Learning
When operating in service of people, robots need to optimize rewards aligned with end-user preferences.
Human-oriented Representation Learning for Robotic Manipulation
We introduce Task Fusion Decoder as a plug-and-play embedding translator that utilizes the underlying relationships among these perceptual skills to guide the representation learning towards encoding meaningful structure for what's important for all perceptual skills, ultimately empowering learning of downstream robotic manipulation tasks.
LanguageMPC: Large Language Models as Decision Makers for Autonomous Driving
Existing learning-based autonomous driving (AD) systems face challenges in comprehending high-level information, generalizing to rare events, and providing interpretability.
RSRD: A Road Surface Reconstruction Dataset and Benchmark for Safe and Comfortable Autonomous Driving
This paper addresses the growing demands for safety and comfort in intelligent robot systems, particularly autonomous vehicles, where road conditions play a pivotal role in overall driving performance.
HallE-Control: Controlling Object Hallucination in Large Multimodal Models
Current Large Multimodal Models (LMMs) achieve remarkable progress, yet there remains significant uncertainty regarding their ability to accurately apprehend visual details, that is, in performing detailed captioning.
Robust 6DoF Pose Estimation Against Depth Noise and a Comprehensive Evaluation on a Mobile Dataset
In this paper, we extensively investigate the robustness of existing RGBD-based 6DoF pose estimation methods against varying levels of depth sensor noise.
Ranked #1 on
6D Pose Estimation
on DTTD-Mobile
Pre-training on Synthetic Driving Data for Trajectory Prediction
Accumulating substantial volumes of real-world driving data proves pivotal in the realm of trajectory forecasting for autonomous driving.
DELFlow: Dense Efficient Learning of Scene Flow for Large-Scale Point Clouds
Previous methods rarely predict scene flow from the entire point clouds of the scene with one-time inference due to the memory inefficiency and heavy overhead from distance calculation and sorting involved in commonly used farthest point sampling, KNN, and ball query algorithms for local feature aggregation.
NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detection
We present NeRF-Det, a novel method for indoor 3D detection with posed RGB images as input.
Quadric Representations for LiDAR Odometry, Mapping and Localization
Current LiDAR odometry, mapping and localization methods leverage point-wise representations of 3D scenes and achieve high accuracy in autonomous driving tasks.
SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object Detection
However, given that objects occupy only a small part of a scene, finding dense candidates and generating dense representations is noisy and inefficient.
Open-Vocabulary Point-Cloud Object Detection without 3D Annotation
In this paper, we address open-vocabulary 3D point-cloud detection by a dividing-and-conquering strategy, which involves: 1) developing a point-cloud detector that can learn a general representation for localizing various objects, and 2) connecting textual and point-cloud representations to enable the detector to classify novel object categories based on text prompting.
Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detection
While recent camera-only 3D detection methods leverage multiple timesteps, the limited history they use significantly hampers the extent to which temporal fusion can improve object perception.
Ranked #1 on
Robust Camera Only 3D Object Detection
on nuScenes-C
Open-Vocabulary 3D Detection via Image-level Class and Debiased Cross-modal Contrastive Learning
Current point-cloud detection methods have difficulty detecting the open-vocabulary objects in the real world, due to their limited generalization capability.
PreTraM: Self-Supervised Pre-training via Connecting Trajectory and Map
It is hard to replicate these approaches in trajectory forecasting due to the lack of adequate trajectory data (e. g., 34K samples in the nuScenes dataset).
DetMatch: Two Teachers are Better Than One for Joint 2D and 3D Semi-Supervised Object Detection
While numerous 3D detection works leverage the complementary relationship between RGB images and point clouds, developments in the broader framework of semi-supervised object recognition remain uninfluenced by multi-modal fusion.
VisDrone-CC2020: The Vision Meets Drone Crowd Counting Challenge Results
Crowd counting on the drone platform is an interesting topic in computer vision, which brings new challenges such as small object inference, background clutter and wide viewpoint.
Image2Point: 3D Point-Cloud Understanding with 2D Image Pretrained Models
We discover that we can indeed use the same architecture and pretrained weights of a neural net model to understand both images and point-clouds.
DCANet: Dense Context-Aware Network for Semantic Segmentation
As the superiority of context information gradually manifests in advanced semantic segmentation, learning to capture the compact context relationship can help to understand the complex scenes.
A Simple and Efficient Multi-task Network for 3D Object Detection and Road Understanding
Detecting dynamic objects and predicting static road information such as drivable areas and ground heights are crucial for safe autonomous driving.
Visual Transformers: Where Do Transformers Really Belong in Vision Models?
A recent trend in computer vision is to replace convolutions with transformers.
Sparse R-CNN: End-to-End Object Detection with Learnable Proposals
In our method, however, a fixed sparse set of learned object proposals, total length of $N$, are provided to object recognition head to perform classification and location.
Ranked #5 on
2D Object Detection
on CeyMo
Visual Transformers: Token-based Image Representation and Processing for Computer Vision
In this work, we challenge this paradigm by (a) representing images as semantic visual tokens and (b) running transformers to densely model token relationships.
SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation
Using standard convolutions to process such LiDAR images is problematic, as convolution filters pick up local features that are only active in specific regions in the image.
Ranked #26 on
3D Semantic Segmentation
on SemanticKITTI
AutoScale: Learning to Scale for Crowd Counting and Localization
A major issue is that the density map on dense regions usually accumulates density values from a number of nearby Gaussian blobs, yielding different large density values on a small set of pixels.
Learn to Scale: Generating Multipolar Normalized Density Maps for Crowd Counting
Dense crowd counting aims to predict thousands of human instances from an image, by calculating integrals of a density map over image pixels.
