Chenfeng Xu

EDBT 2026 Demo / reviewers in the wild / expert

dblp:65/1881 · DBLP profile ↗

← Back

45ranked-venue papers

10as first author

39since 2021 · last 2025

—ORCID · conflict

Domains — the database's venue-derived domains; a paper can count in several

Artificial intelligence and machine learning · 42 · 9 first-author · 38 since 2021Graphics, computer vision, multimedia, augmented reality and games · 20 · 6 first-author · 18 since 2021Systems, architecture and hardware · 7 · 1 first-author · 7 since 2021Applied, interdisciplinary, general and emerging computing · 3 · 1 first-author · 1 since 2021

Year	Publication	Venue	Position
2025	CompGS: Unleashing 2D Compositionality for Compositional Text-to-3D via Dynamically Optimizing 3D Gaussians abstract Recent breakthroughs in text-guided image generation have significantly advanced the field of 3D generation. While generating a single high-quality 3D object is now feasible, generating multiple objects with reasonable interactions within a 3D space, a.k.a. compositional 3D generation, presents substantial challenges. This paper introduces COMPGS, a novel generative framework that employs 3D Gaussian Splatting (GS) for efficient, compositional text-to-3D content generation. 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. COMPGS first automatically decomposes 3D Gaussians into distinct entity parts, enabling optimization at both the entity and composition levels. Additionally, COMPGS optimizes across objects of varying scales by dynamically adjusting the spatial parameters of each entity, enhancing the generation of fine-grained details, particularly in smaller entities. Qualitative comparisons and quantitative evaluations on T3Bench demonstrate the effectiveness of COMPGS in generating compositional 3D objects with superior image quality and semantic alignment over existing methods. COMPGS can also be easily extended to progressively adding 3D objects, facilitating complex scene generation. We hope COMPGS will provide new insights to the compositional 3D generation. Chongjian Ge, Chenfeng Xu, Yuanfeng Ji, Chensheng Peng, Masayoshi Tomizuka, Ping Luo 0002, Mingyu Ding, Varun Jampani	CVPR	2
2025	Segment Any Motion in Videos abstract Moving object segmentation is a crucial task for achieving a high-level understanding of visual scenes and has numerous downstream applications. Humans can effortlessly segment moving objects in videos. Previous work has largely relied on optical flow to provide motion cues; however, this approach often results in imperfect predictions due to challenges such as partial motion, complex deformations, motion blur and background distractions. We propose a novel approach for moving object segmentation that combines long-range trajectory motion cues with DINO-based semantic features and leverages SAM2 for pixel-level mask densification through an iterative prompting strategy. Our model employs Spatio-Temporal Trajectory Attention and Motion-Semantic Decoupled Embedding to prioritize motion while integrating semantic support. Extensive testing on diverse datasets demonstrates state-of-the-art performance, excelling in challenging scenarios and fine-grained segmentation of multiple objects. Our code is available at https://motion-seg.github.io/. Wenzhao Zheng, Chenfeng Xu, Kurt Keutzer, Shanghang Zhang, Angjoo Kanazawa, Qianqian Wang 0002	CVPR	3
2025	DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenes abstract We present DeSiRe-GS, a self-supervised gaussian splatting representation, enabling effective static-dynamic decomposition and high-fidelity surface reconstruction in complex driving scenarios. Our approach employs a two-stage optimization pipeline of dynamic street Gaussians. In the first stage, we extract 2D motion masks based on the observation that 3D Gaussian Splatting inherently can reconstruct only the static regions in dynamic environments. These extracted 2D motion priors are then mapped into the Gaussian space in a differentiable manner, leveraging an efficient formulation of dynamic Gaussians in the second stage. Combined with the introduced geometric regularizations, our method are able to address the over-fitting issues caused by data sparsity in autonomous driving, reconstructing physically plausible Gaussians that align with object surfaces rather than floating in air. Furthermore, we introduce temporal cross-view consistency to ensure coherence across time and viewpoints, resulting in high-quality surface reconstruction. Comprehensive experiments demonstrate the efficiency and effectiveness of DeSiRe-GS, surpassing prior self-supervised arts and achieving accuracy comparable to methods relying on external 3D bounding box annotations. Code is available at https://github.com/chengweialan/DeSiRe-GS Chensheng Peng, Chenfeng Xu, Yichen Xie 0002, Wenzhao Zheng, Kurt Keutzer, Masayoshi Tomizuka	CVPR	4
2025	Bridging Viewpoint Gaps: Geometric Reasoning Boosts Semantic Correspondence abstract Finding semantic correspondences between images is a challenging problem in computer vision, particularly under significant viewpoint changes. Previous methods rely on semantic features from pre-trained 2D models like Stable Diffusion and DINOv2, which often struggle to extract viewpoint-invariant features. To overcome this, we propose a novel approach that integrates geometric and semantic reasoning. Unlike prior methods relying on heuristic geometric enhancements, our framework fine-tunes DUSt3R on synthetic cross-instance data to reconstruct distinct objects in an aligned 3D space. By learning to deform these objects into similar shapes using semantic supervision, we enable efficient KNN-based geometric matching, followed by sparse semantic matching within local KNN candidates. While trained on synthetic data, our method generalizes effectively to real-world images, achieving up to 7.4-point improvements in zero-shot settings on the rigid-body subset of Spair-71K and up to 19.6-point gains under extreme viewpoint variations. Additionally, it accelerates runtime by up to 40 times, demonstrating both its robustness to viewpoint changes and its efficiency for practical applications. Code is available at https://github.com/QiyangQ/Bridge-Viewpoint-Gap. Qiyang Qian, Hansheng Chen 0004, Masayoshi Tomizuka, Kurt Keutzer, Qianqian Wang 0002, Chenfeng Xu	CVPR	6
2025	StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation abstract We introduce StreamDiffusion, a real-time diffusion pipeline designed for interactive image generation. Existing diffusion models are adept at creating images from text or image prompts, yet they often fall short in real-time interaction. This limitation becomes particularly evident in scenarios involving continuous input, such as Metaverse, live video streaming, and broadcasting, where high throughput is imperative. To address this, we present a novel approach that transforms the original sequential denoising into the batching denoising process. Stream Batch eliminates the conventional wait-and-interact approach and enables fluid and high throughput streams. To handle the frequency disparity between data input and model throughput, we design a novel input-output queue for parallelizing the streaming process. Moreover, the existing diffusion pipeline uses classifier-free guidance(CFG), which requires additional U-Net computation. To mitigate the redundant computations, we propose a novel residual classifier-free guidance (RCFG) algorithm that reduces the number of negative conditional denoising steps to only one or even zero. Besides, we introduce a stochastic similarity filter(SSF) to optimize power consumption. Our Stream Batch achieves around 1.5x speedup compared to the sequential denoising method at different denoising levels. The proposed RCFG leads to speeds up to 2.05x higher than the conventional CFG. Combining the proposed strategies and existing mature acceleration tools makes the image-to-image generation achieve up-to 91.07fps on one RTX4090, improving the throughputs of AutoPipline developed by Diffusers over 59.56x. Furthermore, our proposed StreamDiffusion also significantly reduces the energy consumption by 2.39x on one RTX3060 and 1.99x on one RTX4090, respectively. Akio Kodaira, Chenfeng Xu, Toshiki Hazama, Takanori Yoshimoto, Kohei Ohno, Shogo Mitsuhori, Soichi Sugano, Hanying Cho, Masayoshi Tomizuka, Kurt Keutzer	ICCV	2
2025	A Lesson in Splats: Teacher-Guided Diffusion for 3D Gaussian Splats Generation with 2D Supervision abstract We present a novel framework for training 3D image-conditioned diffusion models using only 2D supervision. Recovering 3D structure from 2D images is inherently ill-posed due to the ambiguity of possible reconstructions, making generative models a natural choice. However, most existing 3D generative models rely on full 3D supervision, which is impractical due to the scarcity of large-scale 3D datasets. To address this, we propose leveraging sparse-view supervision as a scalable alternative. While recent reconstruction models use sparse-view supervision with differentiable rendering to lift 2D images to 3D, they are predominantly deterministic, failing to capture the diverse set of plausible solutions and producing blurry predictions in uncertain regions. A key challenge in training 3D diffusion models with 2D supervision is that the standard training paradigm requires both the denoising process and supervision to be in the same modality. We address this by decoupling the noisy samples being denoised from the supervision signal, allowing the former to remain in 3D while the latter is provided in 2D. Our approach leverages suboptimal predictions from a deterministic image-to-3D model-acting as a "teacher"-to generate noisy 3D inputs, enabling effective 3D diffusion training without requiring full 3D ground truth. We validate our framework on both object-level and scene-level datasets, using two different 3D Gaussian Splat (3DGS) teachers. Our results show that our approach consistently improves upon these deterministic teachers, demonstrating its effectiveness in scalable and high-fidelity 3D generative modeling. See our project page at https://lesson-in-splats.github.io/ Chensheng Peng, Ido Sobol, Masayoshi Tomizuka, Kurt Keutzer, Chenfeng Xu, Or Litany	ICCV	5
2025	X-Drive: Cross-modality Consistent Multi-Sensor Data Synthesis for Driving Scenarios abstract Recent advancements have exploited diffusion models for the synthesis of either LiDAR point clouds or camera image data in driving scenarios. Despite their success in modeling single-modality data marginal distribution, there is an under- exploration in the mutual reliance between different modalities to describe com- plex driving scenes. To fill in this gap, we propose a novel framework, X-DRIVE, to model the joint distribution of point clouds and multi-view images via a dual- branch latent diffusion model architecture. Considering the distinct geometrical spaces of the two modalities, X-DRIVE conditions the synthesis of each modality on the corresponding local regions from the other modality, ensuring better alignment and realism. To further handle the spatial ambiguity during denoising, we design the cross-modality condition module based on epipolar lines to adaptively learn the cross-modality local correspondence. Besides, X-DRIVE allows for controllable generation through multi-level input conditions, including text, bounding box, image, and point clouds. Extensive results demonstrate the high-fidelity synthetic results of X-DRIVE for both point clouds and multi-view images, adhering to input conditions while ensuring reliable cross-modality consistency. Our code will be made publicly available at https://github.com/yichen928/X-Drive. Yichen Xie 0002, Chenfeng Xu, Chensheng Peng, Shuqi Zhao, Nhat Ho, Alexander T. Pham, Mingyu Ding, Masayoshi Tomizuka	ICLR	2
2025	Looking Backward: Streaming Video-to-Video Translation with Feature Banks abstract This paper introduces StreamV2V, a diffusion model that achieves real-time streaming video-to-video (V2V) translation with user prompts. Unlike prior V2V methods using batches to process limited frames, we opt to process frames in a streaming fashion, to support unlimited frames. At the heart of StreamV2V lies a backward-looking principle that relates the present to the past. This is realized by maintaining a feature bank, which archives information from past frames. For incoming frames, StreamV2V extends self-attention to include banked keys and values, and directly fuses similar past features into the output. The feature bank is continually updated by merging stored and new features, making it compact yet informative. StreamV2V stands out for its adaptability and efficiency, seamlessly integrating with image diffusion models without fine-tuning. It can run 20 FPS on one A100 GPU, being 15$\times$, 46$\times$, 108$\times$, and 158$\times$ faster than FlowVid, CoDeF, Rerender, and TokenFlow, respectively. Quantitative metrics and user studies confirm StreamV2V's exceptional ability to maintain temporal consistency. Akio Kodaira, Chenfeng Xu, Masayoshi Tomizuka, Kurt Keutzer, Diana Marculescu	ICLR	3
2025	Dobi-SVD: Differentiable SVD for LLM Compression and Some New Perspectives abstract Large language models (LLMs) have sparked a new wave of AI applications; however, their substantial computational costs and memory demands pose significant challenges to democratizing access to LLMs for a broader audience. Singular Value Decomposition (SVD), a technique studied for decades, offers a hardware-independent and flexibly tunable solution for LLM compression. In this paper, we present new directions using SVD: we first theoretically analyze the optimality of truncating weights and truncating activations, then we further identify three key issues on SVD-based LLM compression, including (1) How can we determine the optimal truncation position for each weight matrix in LLMs? (2) How can we efficiently update the weight matrices based on truncation position? (3) How can we address the inherent "injection" nature that results in the information loss of the SVD? We propose an effective approach, Dobi-SVD, to tackle the three issues. First, we propose a differentiable truncation-value learning mechanism, along with gradient-robust backpropagation, enabling the model to adaptively find the optimal truncation positions. Next, we utilize the Eckart-Young-Mirsky theorem to derive a theoretically optimal weight update formula through rigorous mathematical analysis. Lastly, by observing and leveraging the quantization-friendly nature of matrices after SVD decomposition, we reconstruct a mapping between truncation positions and memory requirements, establishing a bijection from truncation positions to memory. Experimental results show that with a 40\% parameter-compression rate, our method achieves a perplexity of 9.07 on the Wikitext2 dataset with the compressed LLama-7B model, a 78.7\% improvement over the state-of-the-art SVD for LLM compression method. We emphasize that Dobi-SVD is the first to achieve such a high-ratio LLM compression with minimal performance drop. We also extend our Dobi-SVD to VLM compression, achieving a 20\% increase in throughput with minimal performance degradation. We hope that the inference speedup—up to 12.4x on 12GB NVIDIA Titan Xp GPUs and 3x on 80GB A100 GPUs for LLMs, and 1.2x on 80GB A100 GPUs for VLMs—will bring significant benefits to the broader community such as robotics. Qinsi Wang, Jinghan Ke, Masayoshi Tomizuka, Kurt Keutzer, Chenfeng Xu	ICLR	5
2025	WOMD-Reasoning: A Large-Scale Dataset for Interaction Reasoning in Driving abstract Language models uncover unprecedented abilities in analyzing driving scenarios, owing to their limitless knowledge accumulated from text-based pre-training. Naturally, they should particularly excel in analyzing rule-based interactions, such as those triggered by traffic laws, which are well documented in texts. However, such interaction analysis remains underexplored due to the lack of dedicated language datasets that address it. Therefore, we propose Waymo Open Motion Dataset-Reasoning (WOMD-Reasoning), a comprehensive large-scale Q&As dataset built on WOMD focusing on describing and reasoning traffic rule-induced interactions in driving scenarios. WOMD-Reasoning also presents by far the largest multi-modal Q&A dataset, with 3 million Q&As on real-world driving scenarios, covering a wide range of driving topics from map descriptions and motion status descriptions to narratives and analyses of agents' interactions, behaviors, and intentions. To showcase the applications of WOMD-Reasoning, we design Motion-LLaVA, a motion-language model fine-tuned on WOMD-Reasoning. Quantitative and qualitative evaluations are performed on WOMD-Reasoning dataset as well as the outputs of Motion-LLaVA, supporting the data quality and wide applications of WOMD-Reasoning, in interaction predictions, traffic rule compliance plannings, etc. The dataset and its vision modal extension are available on https://waymo.com/open/download/. The codes & prompts to build it are available on https://github.com/yhli123/WOMD-Reasoning. Cunxin Fan, Chongjian Ge, Seth Z. Zhao, Chenran Li, Chenfeng Xu, Huaxiu Yao, Masayoshi Tomizuka, Bolei Zhou, Chen Tang 0001, Mingyu Ding	ICML	6
2025	Sparse Video-Gen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity abstract 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. This inefficiency primarily arises from the quadratic computational complexity of 3D full attention with respect to the context length. In this paper, we propose a training-free framework termed Sparse VideoGen (SVG) that leverages the inherent sparsity in 3D full attention to boost inference efficiency. We reveal that the attention heads can be dynamically classified into two groups depending on distinct sparse patterns: (1) Spatial Head, where only spatially-related tokens within each frame dominate the attention output, and (2) Temporal Head, where only temporally-related tokens across different frames dominate. Based on this insight, SVG proposes an online profiling strategy to capture the dynamic sparse patterns and predicts the type of attention head. Combined with a novel hardware-efficient tensor layout transformation and customized kernel implementations, SVG achieves up to 2.28$\times$ and 2.33$\times$ end-to-end speedup on CogVideoX-v1.5 and HunyuanVideo, respectively, while preserving generation quality. Our code will be open-sourced upon publication. Haocheng Xi, Shuo Yang 0011, Yilong Zhao 0002, Chenfeng Xu, Xiuyu Li, Yujun Lin 0001, Han Cai, Dacheng Li, Jianfei Chen 0001, Ion Stoica, Kurt Keutzer, Song Han 0003	ICML	4
2025	TrajSSL: Trajectory-Enhanced Semi-Supervised 3D Object Detection abstract Semi-supervised 3D object detection is a common strategy employed to circumvent the challenge of manually labeling large-scale autonomous driving perception datasets. Pseudo-labeling approaches to semi-supervised learning adopt a teacher-student framework in which machine-generated pseudo-labels on a large unlabeled dataset are used in combination with a small manually-labeled dataset for training. In this work, we address the problem of improving pseudo-label quality through leveraging long- term temporal information captured in driving scenes. More specifically, we leverage pre-trained motion-forecasting models to generate object trajectories on pseudo-labeled data to further enhance the student model training. Our approach improves pseudo-label quality in two distinct manners: first, we suppress false positive pseudo-labels through establishing consistency across multiple frames of motion forecasting outputs. Second, we compensate for false negative detections by directly inserting predicted object tracks into the pseudo-labeled scene. Experiments on the nuScenes dataset demonstrate the effectiveness of our approach, improving the performance of standard semi-supervised approaches in a variety of settings. Philip L. Jacobson, Yichen Xie 0002, Mingyu Ding, Chenfeng Xu, Masayoshi Tomizuka, Ming C. Wu	ICRA	4
2025	CooPre: Cooperative Pretraining for V2X Cooperative Perception abstract Existing Vehicle-to-Everything (V2X) cooperative perception methods rely on accurate multi-agent 3D annotations. Nevertheless, it is time-consuming and expensive to collect and annotate real-world data, especially for V2X systems. In this paper, we present a self-supervised learning framwork for V2X cooperative perception, which utilizes the vast amount of unlabeled 3D V2X data to enhance the perception performance. Specifically, multi-agent sensing information is aggregated to form a holistic view and a novel proxy task is formulated to reconstruct the LiDAR point clouds across multiple connected agents to better reason multi-agent spatial correlations. Besides, we develop a V2X bird-eye-view (BEV) guided masking strategy which effectively allows the model to pay attention to 3D features across heterogeneous V2X agents (i.e., vehicles and infrastructure) in the BEV space. Noticeably, such a masking strategy effectively pretrains the 3D encoder with a multi-agent LiDAR point cloud reconstruction objective and is compatible with mainstream cooperative perception backbones. Our approach, validated through extensive experiments on representative datasets (i.e., V2X-Real, V2V4Real, and OPV2V) and multiple state-of-the-art cooperative perception methods (i.e., AttFuse, F-Cooper, and V2X-ViT), leads to a performance boost across all V2X settings. Notably, CooPre achieves a 4% mAP improvement on V2X-Real dataset and surpasses baseline performance using only 50% of the training data, highlighting its data efficiency. Additionally, we demonstrate the framework’s powerful performance in cross-domain transferability and robustness under challenging scenarios. The code will be made publicly available at https://github.com/ucla-mobility/CooPre. Seth Z. Zhao, Hao Xiang 0001, Chenfeng Xu, Xin Xia 0007, Bolei Zhou, Jiaqi Ma 0003	IROS	3
2025	Angles Don't Lie: Unlocking Training‑Efficient RL Through the Model's Own Signals abstract Current Reinforcement Fine-tuning (RFT) paradigms for Large Language Models (LLMs) suffer from sample inefficiency due to the redundant exposure of identical queries under uniform data sampling. While previous work has explored curriculum learning via heuristic difficulty metrics, these strategies exhibit limitations by neglecting the intrinsic learning signals generated by the model itself, thus leading to suboptimal training regimes. In this paper, we identify a model-inherent signal termed angle concentration that effectively reflects an LLM's capacity to learn from specific data. We theoretically and empirically demonstrate a correlation between the angular distribution of token hidden state vectors and the resulting gradient, revealing a learning preference for data exhibiting higher angle concentration. Inspired by this finding, we propose GAIN-RL, a Gradient-driven Angle-Informed Navigated RL framework. By leveraging the model's intrinsic angle concentration signal, GAIN-RL dynamically selects training data in each epoch, ensuring consistently impactful gradient updates and thus significantly enhancing overall training efficiency. Empirical evaluations show that GAIN-RL (GRPO) achieves over a 2.5$\times$ acceleration in training efficiency across diverse mathematical and coding tasks and varying model scales. Furthermore, GAIN-RL (GRPO)'s efficient sampling yields data-efficient training, achieving better performance with half the original data compared to vanilla GRPO with full training data. Qinsi Wang, Jinghan Ke, Hancheng Ye, Yueqian Lin, Yuzhe Fu, Kurt Keutzer, Chenfeng Xu, Yiran Chen 0001	NeurIPS	8
2025	Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation abstract Diffusion Transformers (DiTs) are essential for video generation but suffer from significant latency due to the quadratic complexity of attention. By computing only critical tokens, sparse attention reduces computational costs and offers a promising acceleration approach. However, we identify that existing methods fail to approach optimal generation quality under the same computation budget for two reasons: (1) Inaccurate critical token identification: current methods cluster tokens based on position rather than semantics, leading to imprecise aggregated representations. (2) Excessive computation waste: critical tokens are scattered among non-critical ones, leading to wasted computation on GPUs, which are optimized for processing contiguous tokens. 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. The core of SVG2 is semantic-aware permutation, which clusters and reorders tokens based on semantic similarity using k-means. This approach ensures both a precise cluster representation, improving identification accuracy, and a densified layout of critical tokens, enabling efficient computation without padding. Additionally, SVG2 integrates Top-p dynamic budget control and customized kernel implementations, achieving up to $2.30\times$ and $1.89\times$ speedup while maintaining a PSNR of up to $30$ and $26$ on HunyuanVideo and Wan 2.1, respectively. Our code is open-sourced at https://github.com/svg-project/Sparse-VideoGen. Shuo Yang 0011, Haocheng Xi, Yilong Zhao 0002, Han Cai, Yujun Lin 0001, Xiuyu Li, Chenfeng Xu, Kelly Peng, Jianfei Chen 0001, Song Han 0003, Kurt Keutzer, Ion Stoica	NeurIPS	9
2025	Representation of Human arm Dynamic Intents With an Electrical Impedance Tomography (EIT)-Driven Musculoskeletal Model for Human-Robot Interaction abstract Representing human arm dynamic intent is essential for efective human-robot interaction. Accurately and robustly decoding these intentions through mathematical modeling of neuromuscular processes poses signifcant challenges. This study introduces an EIT-driven musculoskeletal model which integrates an EIT sensing system with methods for muscle identifcation, parameter estimation, and musculoskeletal system modeling. Unlike existing muscle-signal techniques, EIT captures muscle activities from the anatomical cross-sectional plane, providing both activation dynamics and morphological features. We validated our method through multi-DoF wrist kinematics estimation under varying contraction intensities, arm endpoint stifness estimation, and robotic variable admittance control. Our approach achieves accuracy comparable to state-of-the-art methods while requiring fewer training samples and a more compact sensing system. The model incorporates physiological constraints, minimizing decoding errors and ensuring interaction safety. This method enables reliable intent decoding with practical training demands. Future work will enhance the EIT system for complex tasks. Enhao Zheng, Chenfeng Xu, Qining Wang	IEEE Trans. Robotics	3
2024	3DiffTection: 3D Object Detection with Geometry-Aware Diffusion Features abstract 3DiffTection introduces a novel method for 3D object detection from single images, utilizing a 3D-aware diffusion model for feature extraction. Addressing the resource-intensive nature of annotating large-scale 3D image data, our approach leverages pretrained diffusion models, traditionally used for 2D tasks, and adapts them for 3D detection through geometric and semantic tuning. Geometrically, we enhance the model to perform view synthesis from single images, incorporating an epipolar warp operator. This process utilizes easily accessible posed image data, eliminating the need for manual annotation. Semantically, the model is further refined on target detection data. Both stages utilize ControlNet, ensuring the preservation of original feature capabilities. Through our methodology, we obtain 3D-aware features that excel in identifying cross-view point correspondences. In 3D detection, 3DiffTection substantially surpasses previous benchmarks, e.g., Cube-RCNN, by 9.43% in AP3D on the Omni3D-ARkitscene dataset. Furthermore, 3DiffTection demonstrates robust label efficiency and generalizes well to cross-domain data, nearly matching fully-supervised models in zero-shot scenarios. Project page: https://research.nvidia.com/labs/toronto-ai/3difftection/. Chenfeng Xu, Huan Ling, Sanja Fidler, Or Litany	CVPR	1
2024	Sparse Refinement for Efficient High-Resolution Semantic Segmentation Zhuoyang Zhang, Samir Khaki, Shang Yang, Haotian Tang, Chenfeng Xu, Kurt Keutzer, Song Han 0003	ECCV (67)	6
2024	CVT-Occ: Cost Volume Temporal Fusion for 3D Occupancy Prediction Zhangchen Ye, Chenfeng Xu, Yiming Li 0003, Hang Zhao 0021	ECCV (73)	3
2024	What Matters to You? Towards Visual Representation Alignment for Robot Learning abstract When operating in service of people, robots need to optimize rewards aligned with end-user preferences. Since robots will rely on raw perceptual inputs, their rewards will inevitably use visual representations. Recently there has been excitement in using representations from pre-trained visual models, but key to making these work in robotics is fine-tuning, which is typically done via proxy tasks like dynamics prediction or enforcing temporal cycle-consistency. However, all these proxy tasks bypass the human’s input on what matters to them, exacerbating spurious correlations and ultimately leading to behaviors that are misaligned with user preferences. In this work, we propose that robots should leverage human feedback to align their visual representations with the end-user and disentangle what matters for the task. We propose Representation-Aligned Preference-based Learning (RAPL), a method for solving the visual representation alignment problem and visual reward learning problem through the lens of preference-based learning and optimal transport. Across experiments in X MAGICAL and in robotic manipulation, we find that RAPL’s reward consistently generates preferred robot behaviors with high sample efficiency, and shows strong zero-shot generalization when the visual representation is learned from a different embodiment than the robot’s. Thomas Tian, Chenfeng Xu, Masayoshi Tomizuka, Jitendra Malik, Andrea Bajcsy	ICLR	2
2024	Open X-Embodiment: Robotic Learning Datasets and RT-X Models : Open X-Embodiment Collaboration abstract Large, high-capacity models trained on diverse datasets have shown remarkable successes on efficiently tackling downstream applications. In domains from NLP to Computer Vision, this has led to a consolidation of pretrained models, with general pretrained backbones serving as a starting point for many applications. Can such a consolidation happen in robotics? Conventionally, robotic learning methods train a separate model for every application, every robot, and even every environment. Can we instead train "generalist" X-robot policy that can be adapted efficiently to new robots, tasks, and environments? In this paper, we provide datasets in standardized data formats and models to make it possible to explore this possibility in the context of robotic manipulation, alongside experimental results that provide an example of effective X-robot policies. We assemble a dataset from 22 different robots collected through a collaboration between 21 institutions, demonstrating 527 skills (160266 tasks). We show that a high-capacity model trained on this data, which we call RT-X, exhibits positive transfer and improves the capabilities of multiple robots by leveraging experience from other platforms. The project website is robotics-transformer-x.github.io. Abigail O'Neill, Abhiram Maddukuri, Abhishek Gupta 0004, Abhishek Padalkar, Abraham Lee, Acorn Pooley, Agrim Gupta, Ajay Mandlekar, Ajinkya Jain, Albert Tung, Alex Bewley, Alex Irpan, Alexander Khazatsky, Anant Rai, Anchit Gupta, Andrew E. Wang, Anikait Singh, Animesh Garg, Aniruddha Kembhavi, Annie Xie, Anthony Brohan, Antonin Raffin, Archit Sharma, Arefeh Yavary, Arhan Jain, Ashwin Balakrishna, Ayzaan Wahid, Ben Burgess-Limerick, Bernhard Schölkopf, Blake Wulfe, Brian Ichter, Cewu Lu, Charles Xu 0003, Charlotte Le, Chelsea Finn, Chen Wang 0053, Chenfeng Xu, Cheng Chi 0001, Chenguang Huang, Christine Chan, Christopher Agia, Chuer Pan, Chuyuan Fu, Coline Devin, Danfei Xu, Daniel Morton, Danny Drieß, Daphne Chen, Deepak Pathak, Dhruv Shah, Dieter Büchler, Dinesh Jayaraman, Dmitry Kalashnikov, Dorsa Sadigh, Edward Johns, Ethan Paul Foster, Fangchen Liu, Federico Ceola, Fei Xia 0002, Feiyu Zhao, Freek Stulp, Gaoyue Zhou, Gaurav S. Sukhatme, Gautam Salhotra, Gilbert Feng, Giulio Schiavi, Glen Berseth, Gregory Kahn, Guanzhi Wang, Hao Su 0001, Haoshu Fang, Henghui Bao, Heni Ben Amor, Henrik I. Christensen, Hiroki Furuta, Homer Walke, Hongjie Fang, Huy Ha, Igor Mordatch, Ilija Radosavovic, Isabel Leal, Jacky Liang, Jad Abou-Chakra, Jaehyung Kim 0001, Jaimyn Drake, Jan Peters 0001, Jan Schneider 0007, Jasmine Hsu, Jeannette Bohg, Jeffrey T. Bingham, Jensen Gao, Jiaheng Hu, Jiajun Wu 0001, Jiankai Sun, Jianlan Luo, Jiayuan Gu, Jie Tan 0001, Jihoon Oh, Jimmy Wu, Jingpei Lu, Jitendra Malik, João Silvério, Joey Hejna, Jonathan Booher, Jonathan Tompson, Jonathan Yang, Jordi Salvador, Joseph J. Lim, Junhyek Han, Kanishka Rao, Karl Pertsch, Karol Hausman, Keegan Go, Keerthana Gopalakrishnan, Kenneth Y. Goldberg, Kendra Byrne, Kenneth Oslund, Kento Kawaharazuka, Kevin Black, Kevin Zhang 0002, Kiana Ehsani, Kiran Lekkala, Kirsty Ellis, Krishan Rana, Krishnan Srinivasan, Kuan Fang, Kunal Pratap Singh, Kuo-Hao Zeng, Kyle Hatch, Kyle Hsu, Laurent Itti, Yunliang Chen 0001, Lerrel Pinto, Li Fei-Fei 0001, Liam Tan, Linxi Fan, Lionel Ott, Lisa Lee, Luca Weihs, Magnum Chen, Marion Lepert, Marius Memmel, Masayoshi Tomizuka, Masha Itkina, Mateo Guaman Castro, Max Spero, Maximilian Du, Michael Ahn, Michael C. Yip, Mingtong Zhang 0003, Mingyu Ding, Minho Heo, Mohan Kumar Srirama, Mohit Sharma 0001, Moo Jin Kim, Naoaki Kanazawa, Nicklas Hansen 0001, Nicolas Heess, Nikhil J. Joshi, Niko Sünderhauf, Norman Di Palo, Nur Muhammad Shafiullah, Oier Mees, Oliver Kroemer, Osbert Bastani, Pannag R. Sanketi, Patrick Tree Miller, Patrick Yin, Paul Wohlhart, Peng Xu 0010, Peter David Fagan, Peter Mitrano, Pierre Sermanet, Pieter Abbeel, Priya Sundaresan, Qiuyu Chen, Rafael Rafailov, Ria Doshi, Roberto Martin Martin, Rohan Baijal, Rosario Scalise, Rose Hendrix, Roy Lin, Runjia Qian, Russell Mendonca, Rutav Shah, Ryan Hoque, Ryan Julian, Samuel Bustamante-Gomez, Sean Kirmani, Sergey Levine, Sherry Moore, Shikhar Bahl, Shivin Dass, Shubham D. Sonawani, Shuran Song, Sichun Xu, Siddhant Haldar, Siddharth Karamcheti, Simeon Adebola, Simon Guist, Soroush Nasiriany, Stefan Schaal, Stefan Welker, Stephen Tian, Subramanian Ramamoorthy, Sudeep Dasari, Suneel Belkhale, Sungjae Park, Suraj Nair 0003, Suvir Mirchandani, Takayuki Osa, Tanmay Gupta, Tatsuya Harada, Tatsuya Matsushima, Ted Xiao, Thomas Kollar, Tianhe Yu, Tianli Ding, Todor Davchev, Tony Z. Zhao, Travis Armstrong, Trevor Darrell, Trinity Chung, Vidhi Jain, Vincent Vanhoucke, Wolfram Burgard, Xiaolong Wang 0004, Xinghao Zhu, Xinyang Geng, Liangwei Xu, Yecheng Jason Ma 0001, Yejin Kim 0003, Yevgen Chebotar, Yilin Wu 0003, Yonatan Bisk, Yoonyoung Cho, Youngwoon Lee, Yuchen Cui, Yueh-Hua Wu, Yujin Tang, Yuke Zhu, Yunchu Zhang, Yunfan Jiang 0001, Yunshuang Li, Yunzhu Li, Yusuke Iwasawa, Yutaka Matsuo, Zehan Ma, Zichen Jeff Cui, Zichen Zhang 0016, Zipeng Lin	ICRA	40
2024	Pre-training on Synthetic Driving Data for Trajectory Prediction abstract Accumulating substantial volumes of real-world driving data proves pivotal in the realm of trajectory forecasting for autonomous driving. Given the heavy reliance of current trajectory forecasting models on data-driven methodologies, we aim to tackle the challenge of learning general trajectory forecasting representations under limited data availability. We propose a pipeline-level solution to mitigate the issue of data scarcity in trajectory forecasting. The solution is composed of two parts: firstly, we adopt HD map augmentation and trajectory synthesis for generating driving data, and then we learn representations by pre-training on them. Specifically, we apply vector transformations to reshape the maps, and then employ a rule-based model to generate trajectories on both original and augmented scenes; thus enlarging the driving data without collecting additional real ones. To foster the learning of general representations within this augmented dataset, we comprehensively explore the different pre-training strategies, including extending the concept of a Masked AutoEncoder (MAE) for trajectory forecasting. Without bells and whistles, our proposed pipeline-level solution is general, simple, yet effective: we conduct extensive experiments to demonstrate the effectiveness of our data expansion and pre-training strategies, which outperform the baseline prediction model by large margins, e.g. 5.04%, 3.84% and 8.30% in terms of MR6, minADE6and minFDE6. The pre-training dataset and the codes for pre-training and fine-tuning are released at https://github.com/yhli123/Pretraining_on_Synthetic_Driving_Data_for_Trajectory_Prediction. Seth Z. Zhao, Chenfeng Xu, Chen Tang 0001, Chenran Li, Mingyu Ding, Masayoshi Tomizuka	IROS	3
2024	DSLO: Deep Sequence LiDAR Odometry Based on Inconsistent Spatio-temporal Propagation abstract This paper introduces a 3D point cloud sequence learning model based on inconsistent spatio-temporal propagation for LiDAR odometry, termed DSLO. 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. First, spatial features are encoded using a point feature pyramid, with features reused in successive pose estimations to reduce computational overhead. Second, a sequential pose initialization method is introduced, leveraging the high-frequency sampling characteristic of LiDAR to initialize the LiDAR pose. Then, a gated hierarchical pose refinement mechanism refines poses from coarse to fine by selectively retaining or discarding motion information from different layers based on gate estimations. Finally, temporal feature propagation is proposed to incorporate the historical motion information from point cloud sequences, and address the spatial inconsistency issue when transmitting motion information embedded in point clouds between frames. Experimental results on the KITTI odometry dataset and Argoverse dataset demonstrate that DSLO outperforms state-of-the-art methods, achieving at least a 15.67% improvement on RTE and a 12.64% improvement on RRE, while also achieving a 34.69% reduction in runtime compared to baseline methods. Our implementation will be available at https://github.com/IRMVLab/DSLO. Guangming Wang 0001, Xinrui Wu, Chenfeng Xu, Mingyu Ding, Masayoshi Tomizuka, Hesheng Wang 0001	IROS	4
2024	Immiscible Diffusion: Accelerating Diffusion Training with Noise Assignment abstract In this paper, we point out that suboptimal noise-data mapping leads to slow training of diffusion models. During diffusion training, current methods diffuse each image across the entire noise space, resulting in a mixture of all images at every point in the noise layer. We emphasize that this random mixture of noise-data mapping complicates the optimization of the denoising function in diffusion models. 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. In physics, miscibility can vary according to various intermolecular forces. Thus, immiscibility means that the mixing of molecular sources is distinguishable. Inspired by this concept, we propose an assignment-then-diffusion training strategy to achieve Immiscible Diffusion. As one example, prior to diffusing the image data into noise, we assign diffusion target noise for the image data by minimizing the total image-noise pair distance in a mini-batch. The assignment functions analogously to external forces to expel the diffuse-able areas of images, thus mitigating the inherent difficulties in diffusion training. Our approach is remarkably simple, requiring only one line of code to restrict the diffuse-able area for each image while preserving the Gaussian distribution of noise. In this way, each image is preferably projected to nearby noise. To address the high complexity of the assignment algorithm, we employ a quantized assignment strategy, which significantly reduces the computational overhead to a negligible level (e.g. 22.8ms for a large batch size of 1024 on an A6000). Experiments demonstrate that our method can achieve up to 3x faster training for unconditional Consistency Models on the CIFAR dataset, as well as for DDIM and Stable Diffusion on CelebA and ImageNet dataset, and in class-conditional training and fine-tuning. In addition, we conducted a thorough analysis that sheds light on how it improves diffusion training speed while improving fidelity. The code is available at https://yhli123.github.io/immiscible-diffusion Heyang Jiang, Akio Kodaira, Masayoshi Tomizuka, Kurt Keutzer, Chenfeng Xu	NeurIPS	6
2024	Zero-to-Hero: Enhancing Zero-Shot Novel View Synthesis via Attention Map Filtering abstract Generating realistic images from arbitrary views based on a single source image remains a significant challenge in computer vision, with broad applications ranging from e-commerce to immersive virtual experiences. Recent advancements in diffusion models, particularly the Zero-1-to-3 model, have been widely adopted for generating plausible views, videos, and 3D models. However, these models still struggle with inconsistencies and implausibility in new views generation, especially for challenging changes in viewpoint. In this work, we propose Zero-to-Hero, a novel test-time approach that enhances view synthesis by manipulating attention maps during the denoising process of Zero-1-to-3. By drawing an analogy between the denoising process and stochastic gradient descent (SGD), we implement a filtering mechanism that aggregates attention maps, enhancing generation reliability and authenticity. This process improves geometric consistency without requiring retraining or significant computational resources. Additionally, we modify the self-attention mechanism to integrate information from the source view, reducing shape distortions. These processes are further supported by a specialized sampling schedule. Experimental results demonstrate substantial improvements in fidelity and consistency, validated on a diverse set of out-of-distribution objects. Additionally, we demonstrate the general applicability and effectiveness of Zero-to-Hero in multi-view, and image generation conditioned on semantic maps and pose. Ido Sobol, Chenfeng Xu, Or Litany	NeurIPS	2
2023	Open-Vocabulary Point-Cloud Object Detection without 3D Annotation abstract The goal of open-vocabulary detection is to identify novel objects based on arbitrary textual descriptions. 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. Specifically, we resort to rich image pretrained models, by which the point-cloud detector learns localizing objects under the supervision of predicted 2D bounding boxes from 2D pretrained detectors. Moreover, we propose a novel de-biased triplet cross-modal contrastive learning to connect the modalities of image, point-cloud and text, thereby enabling the point-cloud detector to benefit from vision-language pretrained models, i.e., CLIP. The novel use of image and vision-language pretrained models for point-cloud detectors allows for open-vocabulary 3D object detection without the need for 3D annotations. Experiments demonstrate that the proposed method improves at least 3.03 points and 7.47 points over a wide range of baselines on the ScanNet and SUN RGB-D datasets, respectively. Furthermore, we provide a comprehensive analysis to explain why our approach works. Code is available at https://github.com/lyhdet/OV-3DET Yuheng Lu, Chenfeng Xu, Xiaobao Wei, Masayoshi Tomizuka, Kurt Keutzer, Shanghang Zhang	CVPR	2
2023	DELFlow: Dense Efficient Learning of Scene Flow for Large-Scale Point Clouds abstract Point clouds are naturally sparse, while image pixels are dense. The inconsistency limits feature fusion from both modalities for point-wise scene flow estimation. 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. To mitigate these issues in scene flow learning, we regularize raw points to a dense format by storing 3D coordinates in 2D grids. Unlike the sampling operation commonly used in existing works, the dense 2D representation 1) preserves most points in the given scene, 2) brings in a significant boost of efficiency, and 3) eliminates the density gap between points and pixels, allowing us to perform effective feature fusion. We also present a novel warping projection technique to alleviate the information loss problem resulting from the fact that multiple points could be mapped into one grid during projection when computing cost volume. Sufficient experiments demonstrate the efficiency and effectiveness of our method, outperforming the prior-arts on the FlyingThings3D and KITTI dataset. Our source codes will be released on https://github.com/IRMVLab/DELFlow. Chensheng Peng, Guangming Wang 0001, Xian Wan Lo, Xinrui Wu, Chenfeng Xu, Masayoshi Tomizuka, Hesheng Wang 0001	ICCV	5
2023	SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object Detection abstract By identifying four important components of existing LiDAR-camera 3D object detection methods (LiDAR and camera candidates, transformation, and fusion outputs), we observe that all existing methods either find dense candidates or yield dense representations of scenes. However, given that objects occupy only a small part of a scene, finding dense candidates and generating dense representations is noisy and inefficient. We propose SparseFusion, a novel multi-sensor 3D detection method that exclusively uses sparse candidates and sparse representations. Specifically, SparseFusion utilizes the outputs of parallel detectors in the LiDAR and camera modalities as sparse candidates for fusion. We transform the camera candidates into the LiDAR coordinate space by disentangling the object representations. Then, we can fuse the multi-modality candidates in a unified 3D space by a lightweight self-attention module. To mitigate negative transfer between modalities, we propose novel semantic and geometric cross-modality transfer modules that are applied prior to the modality-specific detectors. SparseFusion achieves state-of-the-art performance on the nuScenes benchmark while also running at the fastest speed, even outperforming methods with stronger backbones. We perform extensive experiments to demonstrate the effectiveness and efficiency of our modules and overall method pipeline. Our code will be made publicly available at https://github.com/yichen928/SparseFusion. Yichen Xie 0002, Chenfeng Xu, Marie-Julie Rakotosaona, Patrick Rim, Federico Tombari, Kurt Keutzer, Masayoshi Tomizuka	ICCV	2
2023	NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detection abstract We present NeRF-Det, a novel method for indoor 3D detection with posed RGB images as input. Unlike existing indoor 3D detection methods that struggle to model scene geometry, our method makes novel use of NeRF in an end-to-end manner to explicitly estimate 3D geometry, thereby improving 3D detection performance. Specifically, to avoid the significant extra latency associated with per-scene optimization of NeRF, we introduce sufficient geometry priors to enhance the generalizability of NeRF-MLP. Furthermore, we subtly connect the detection and NeRF branches through a shared MLP, enabling an efficient adaptation of NeRF to detection and yielding geometry-aware volumetric representations for 3D detection. Our method outperforms state-of-the-arts by 3.9 mAP and 3.1 mAP on the ScanNet and ARKITScenes benchmarks, respectively. We provide extensive analysis to shed light on how NeRF-Det works. As a result of our joint-training design, NeRF-Det is able to generalize well to unseen scenes for object detection, view synthesis, and depth estimation tasks without requiring per-scene optimization. Code is available at https://github.com/facebookresearch/NeRF-Det. Chenfeng Xu, Bichen Wu, Ji Hou, Sam S. Tsai, Ruilong Li, Jialiang Wang 0001, Peter Vajda, Kurt Keutzer, Masayoshi Tomizuka	ICCV	1
2023	Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detection Jinhyung Park, Chenfeng Xu, Shijia Yang, Kurt Keutzer, Kris Makoto Kitani, Masayoshi Tomizuka	ICLR	2
2023	Sparse R-CNN: An End-to-End Framework for Object Detection abstract Object detection serves as one of most fundamental computer vision tasks. Existing works on object detection heavily rely on dense object candidates, such as k anchor boxes pre-defined on all grids of an image feature map of size H×W. In this paper, we present Sparse R-CNN, a very simple and sparse method for object detection in images. In our method, a fixed sparse set of learned object proposals ( N in total) are provided to the object recognition head to perform classification and localization. By replacing HWk (up to hundreds of thousands) hand-designed object candidates with N (e.g., 100) learnable proposals, Sparse R-CNN makes all efforts related to object candidates design and one-to-many label assignment completely obsolete. More importantly, Sparse R-CNN directly outputs predictions without the non-maximum suppression (NMS) post-processing procedure. Thus, it establishes an end-to-end object detection framework. Sparse R-CNN demonstrates highly competitive accuracy, run-time and training convergence performance with the well-established detector baselines on the challenging COCO dataset and CrowdHuman dataset. We hope that our work can inspire re-thinking the convention of dense prior in object detectors and designing new high-performance detectors. Peize Sun, Rufeng Zhang, Yi Jiang 0009, Tao Kong, Chenfeng Xu, Masayoshi Tomizuka, Zehuan Yuan, Ping Luo 0002	IEEE Trans. Pattern Anal. Mach. Intell.	5
2022	DetMatch: Two Teachers are Better than One for Joint 2D and 3D Semi-Supervised Object Detection Jinhyung Park, Chenfeng Xu, Yiyang Zhou, Masayoshi Tomizuka	ECCV (10)	2
2022	PreTraM: Self-supervised Pre-training via Connecting Trajectory and Map Chenfeng Xu, Chen Tang 0001, Lingfeng Sun, Kurt Keutzer, Masayoshi Tomizuka, Alireza Fathi	ECCV (39)	1
2022	Image2Point: 3D Point-Cloud Understanding with 2D Image Pretrained Models Chenfeng Xu, Shijia Yang, Tomer Galanti, Bichen Wu, Xiangyu Yue 0001, Bohan Zhai, Peter Vajda, Kurt Keutzer, Masayoshi Tomizuka	ECCV (37)	1
2022	AutoScale: Learning to Scale for Crowd Counting Chenfeng Xu, Dingkang Liang, Yongchao Xu, Song Bai 0001, Xiang Bai, Masayoshi Tomizuka	Int. J. Comput. Vis.	1
2021	Sparse R-CNN: End-to-End Object Detection With Learnable Proposals abstract We present Sparse R-CNN, a purely sparse method for object detection in images. Existing works on object detection heavily rely on dense object candidates, such as k anchor boxes pre-defined on all grids of image feature map of size H × W. 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. By eliminating HWk (up to hundreds of thousands) hand-designed object candidates to N (e.g. 100) learnable proposals, Sparse R-CNN completely avoids all efforts related to object candidates design and many-to-one label assignment. More importantly, final predictions are directly output without non-maximum suppression post-procedure. Sparse R-CNN demonstrates accuracy, run-time and training convergence performance on par with the well-established detector baselines on the challenging COCO dataset, e.g., achieving 45.0 AP in standard 3× training schedule and running at 22 fps using ResNet-50 FPN model. We hope our work could inspire re-thinking the convention of dense prior in object detectors. The code is available at: https://github.com/PeizeSun/SparseR-CNN. Peize Sun, Rufeng Zhang, Yi Jiang 0009, Tao Kong, Chenfeng Xu, Masayoshi Tomizuka, Lei Li 0005, Zehuan Yuan, Changhu Wang, Ping Luo 0002	CVPR	5
2021	Visual Transformers: Where Do Transformers Really Belong in Vision Models? abstract A recent trend in computer vision is to replace convolutions with transformers. However, the performance gain of transformers is attained at a steep cost, requiring GPU years and hundreds of millions of samples for training. This excessive resource usage compensates for a misuse of transformers: Transformers densely model relationships between its inputs - ideal for late stages of a neural network, when concepts are sparse and spatially-distant, but extremely inefficient for early stages of a network, when patterns are redundant and localized. To address these issues, we leverage the respective strengths of both operations, building convolution-transformer hybrids. Critically, in sharp contrast to pixel-space transformers, our Visual Transformer (VT) operates in a semantic token space, judiciously attending to different image parts based on context. Our VTs significantly outperforms baselines: On ImageNet, our VT-ResNets outperform convolution-only ResNet by 4.6 to 7 points and transformer-only ViT-B by 2.6 points with 2.5× fewer FLOPs, 2.1× fewer parameters. For semantic segmentation on LIP and COCO-stuff, VT-based feature pyramid networks (FPN) achieve 0.35 points higher mIoU while reducing the FPN module’s FLOPs by 6.5x. Bichen Wu, Chenfeng Xu, Xiaoliang Dai, Alvin Wan, Peizhao Zhang, Zhicheng Yan 0001, Masayoshi Tomizuka, Joseph Gonzalez 0001, Kurt Keutzer, Peter Vajda	ICCV	2
2021	A Simple and Efficient Multi-task Network for 3D Object Detection and Road Understanding abstract Detecting dynamic objects and predicting static road information such as drivable areas and ground heights are crucial for safe autonomous driving. Previous works studied each perception task separately, and lacked a collective quantitative analysis. In this work, we show that it is possible to perform all perception tasks via a simple and efficient multi-task network. Our proposed network, LidarMTL, takes raw LiDAR point cloud as inputs, and predicts six perception outputs for 3D object detection and road understanding. The network is based on an encoder-decoder architecture with 3D sparse convolution and deconvolution operations. Extensive experiments verify the proposed method with competitive accuracies compared to state-of-the-art object detectors and other task-specific networks. LidarMTL is also leveraged for online localization. Code and pre-trained model have been made available at https://github.com/frankfengdi/LidarMTL. Di Feng, Yiyang Zhou, Chenfeng Xu, Masayoshi Tomizuka	IROS	3
2021	You Only Group Once: Efficient Point-Cloud Processing with Token Representation and Relation Inference Module abstract 3D perception on point-cloud is a challenging and crucial computer vision task. A point-cloud consists of a sparse, unstructured, and unordered set of points. To understand a point-cloud, previous point-based methods, such as PointNet++, extract visual features through the hierarchical aggregation of local features. However, such methods have several critical limitations: 1) They require considerable sampling and grouping operations, which leads to low inference speed. 2) Despite redundancy among adjacent points, they treat all points alike with an equal amount of computation. 3) They aggregate local features together through downsampling, which causes information loss and hurts perception capability. To overcome these challenges, we propose a novel, simple, and elegant deep learning model called YOGO (You Only Group Once). YOGO divides a point-cloud into a small number of parts and extracts a high-dimensional token to represent points within each sub-region. Next, we use self-attention to capture token-to-token relations, and project the token features back to the point features. We formulate such a series of operations as a relation inference module (RIM). Compared with previous methods, YOGO is very efficient because it only needs to sample and group a point-cloud once. Instead of operating on points, YOGO operates on a small number of tokens, each of which summarizes the point features in a sub-region. This allows us to avoid redundant computation and thus boosts efficiency. Moreover, YOGO preserves pointwise features by projecting token features to point features although the RIM computes on tokens. This avoids information loss and enhances point-wise perception capability. We conduct thorough experiments to demonstrate that YOGO achieves at least 3.0x speedup over point-based baselines while delivering competitive classification and segmentation performance on a classification dataset and a segmentation dataset based on 3D Wharehouse, and S3DIS datasets. The code is available at https://github.com/chenfengxu714/YOGO.git. Chenfeng Xu, Bohan Zhai, Bichen Wu, Peter Vajda, Kurt Keutzer, Masayoshi Tomizuka	IROS	1
2020	SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation Chenfeng Xu, Bichen Wu, Peter Vajda, Kurt Keutzer, Masayoshi Tomizuka	ECCV (28)	1
2020	Deep Dual-Stream Network with Scale Context Selection Attention Module for Semantic Segmentation Chenfeng Xu, Chao Chen 0026	Neural Process. Lett.	2
2019	Learn to Scale: Generating Multipolar Normalized Density Maps for Crowd Counting abstract Dense crowd counting aims to predict thousands of human instances from an image, by calculating integrals of a density map over image pixels. Existing approaches mainly suffer from the extreme density variations. Such density pattern shift poses challenges even for multi-scale model ensembling. In this paper, we propose a simple yet effective approach to tackle this problem. First, a patch-level density map is extracted by a density estimation model and further grouped into several density levels which are determined over full datasets. Second, each patch density map is automatically normalized by an online center learning strategy with a multipolar center loss. Such a design can significantly condense the density distribution into several clusters, and enable that the density variance can be learned by a single model. Extensive experiments demonstrate the superiority of the proposed method. Our work outperforms the state-of-the-art by 4.2%, 14.3%, 27.1% and 20.1% in MAE, on the ShanghaiTech Part A, ShanghaiTech Part B, UCF_CC_50 and UCF-QNRF datasets, respectively. Chenfeng Xu, Kai Qiu 0001, Jianlong Fu, Song Bai 0001, Yongchao Xu, Xiang Bai	ICCV	1
2018	Adaptive Fuzzy Logic Control of Fuel-Cell-Battery Hybrid Systems for Electric Vehicles abstract In this paper, we propose an adaptive control approach with fuzzy logic parameter tuning (AFLPT) for the energy management of electric vehicles that are using fuel cell battery hybrid systems. The controller is adaptive to different driving conditions including normal, regenerative, and overload conditions. Specifically, the power flow between the fuel cell (FC) and the Li-ion battery is controlled in real time to maintain the battery state of charge (SOC) at a desirable level while satisfying the FC dynamic constraints. For guaranteeing performance in different driving conditions, the FLPT is integrated with the adaptive controller. Moreover, theoretical properties of the designed controller are analyzed. Simulation and experiment results illustrate the effectiveness of the proposed strategy for FC-battery hybrid systems in electric vehicles. Jian Chen 0005, Chenfeng Xu, Chengshuai Wu	IEEE Trans. Ind. Informatics	2
2011	Evaluation and Optimization of Kernel File Readaheads Based on Markov Decision Models abstract Readahead is an important technique to deal with the huge gap between disk drives and applications. It has become a standard in modern operating systems and advanced storage systems. However, it is difficult to develop the common kernel readahead and to achieve full testing coverage of all cases. In this paper, we formulate the kernel read handling, caching and readahead behavior as an absorbing Markov decision process, and present performance evaluations to compare or verify various readaheads. We also introduce algorithms to find optimal prefetching policies for specific read pattern and present the convergence analysis. By exploiting sample-path-based methods, it becomes much easier to evaluate and optimize prefetching policies, which can provide valuable informations to help the design and improvement of practical readaheads. For illustration and verification, we present two examples and some experiments on the readaheads in Linux kernel. The results show that the model-based evaluations agree with the practice and the improved prefetching policy significantly outperforms the original one in Linux kernel for the specified workloads. Chenfeng Xu, Hongsheng Xi, Fengguang Wu	Comput. J.	1
2008	Event-related optimization for a class of resource location with admission control abstract A class of resource location service for distributed VoD system, which combines one-hop k-random walk and global centralized indexing service, is studied. First, in order to minimizing the cost of communication and guaranteeing the response time performance, a Markov model is proposed to describe the queue phenomenon, admission control and the process of location. In this model, control is related with not only states but also events, which introduce more information as the control basis. Then, an optimization algorithm that combines policy gradient estimation and stochastic approximation is proposed. This algorithm can deal with constraints and depend on no system parameter. Finally, an illustrative simulation is performed to demonstrate the effectiveness of model and algorithm. Chenfeng Xu, Jian Yang 0014, Hongsheng Xi, Baoqun Yin	IJCNN	1