Dense Prediction

Follow this topic Ask about this topic

Momentum

8 papers in the last four weeks, up 60% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 85

All topics

PixelDense: Dense Prediction as Representation Alignment for Pixel Diffusion
Sep 30, 2026Lehan Yang, Daiqing Qi, Wenhao Zhang +9Dense Prediction Diffusion Transformers
University of Virginia · Michigan State University · Adobe +1
Decoupling Spherical Reasoning from Dense Prediction for 360 Depth Estimation
Sep 30, 2026Zhijie Shen, Chunyu Lin, Shuai Zheng +4Depth Estimation Dense Prediction
Beijing Jiaotong University · Hefei University of Technology · Shandong University
FounRef: Robust, Structure-Preserving, and Fast Metric Refinement of Frozen Monocular Foundation Priors with Sparse Anchors
Sep 24, 2026Dan Halperin, Mirko MählischMonocular Depth Estimation 3D Foundation Models
University of the Bundeswehr Munich, Germany
GTR: Gated Token Recurrence for Efficient Dense Prediction
Sep 22, 2026Zhe Feng, Longfei Liu, Wei Liu +7Dense Prediction Self-Supervised Vision Transformers
Didi International Business Group · Intellindust AI Lab · Institute of Automation, Chinese Academy of Sciences +2
LiFR v2: Completion-Augmented Event Propagation for High-Rate Dense Prediction
Sep 22, 2026Tao Wan, Xiaoshan Wu, Yifei Yu +6Dense Prediction Adaptive Feature Fusion
School of Microelectronics, Southern University of Science and Technology, Shenzhen 518055, China · Department of Electrical and Computer Engineering, The University of Hong Kong, Hong Kong, China
Exploring 2D backbone effects for indoor semantic occupancy prediction
Sep 15, 2026Shizhang Fanga, Wanling Yea, Qi Zheng3D Semantic Occupancy Prediction Dense Prediction
aCollege of Electronics and Information Engineering, Shenzhen University, Shenzhen, China
PiPS: Post-Hoc Prototypical Explanations for Interpretable Semantic Segmentation
Sep 15, 2026Miłosz Adamczyk, Tymoteusz Zapala, Piotr Borycki +1Efficient Semantic Segmentation Semantic Segmentation
Jagiellonian University · Wrocław University of Science and Technology · IDEAS Research Institute
From Pixels to Hierarchical Sequences: Quadtree Mask Encoding for Vision-Language Binary Change Detection
Sep 9, 2026Xiao An, Ruikang Zhang, Chen Zhong +4Change Detection Recent Vision-Language Models
Wuhan University · Peking University · Shanghai Artificial Intelligence Laboratory
Efficient Semantic Understanding from Digital Foveation
Sep 3, 2026Caterina Caccavella, Vittorio Fra, Andreas Ziegler +2Dense Prediction Saliency
Zurich University of Applied Sciences (ZHAW), Wädenswil, Switzerland · ETH Zürich, Zürich, Switzerland · Politecnico di Torino, Turin, Italy +2
Pix2Rep-v2: Data-Efficient Representation Learning for Dense Medical Imaging Applications
Sep 1, 2026S. Sifaoui, E. Angelini, S. Toupin +2Self-Supervised Representations Dense Prediction
LTCI, Télécom Paris, Institut Polytechnique de Paris, Palaiseau, France · MIRACL.ai Laboratory, Hôpital Universitaire Lariboisière (AP-HP), Paris, France · Université Paris Cité, Inserm MASCOT, Paris, France
GramLoop: Training-Free Gram-Gated Replay for Robust Dense Prediction
Aug 29, 2026Yang Chen, Canyu Shen, Xinzhe Rao +5Dense Prediction Dinov3
Huazhong University of Science and Technology · Tongji University · King Abdullah University of Science and Technology +2
In-Context Density Estimation for Tabular Data
Aug 10, 2026Patryk Marszałek, Jacek Tabor, Marek ŚmiejaDensity Ratio Estimation Out-Of-Distribution Detection
Faculty of Mathematics and Computer Science, Jagiellonian University, Kraków, Poland
RealDenseFace: Real-time Monocular 3D Face Reconstruction from Dense UV-space Priors
Aug 10, 2026Linzhou Li, Tianjia Shao, Kun ZhouBlind Face Restoration 3D Generation
State Key Lab of CAD&CG, Zhejiang University
HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers
Aug 7, 2026Dong Liu, Yanxuan Yu, Renata Borovica-Gajic +2Self-Supervised Vision Transformers Vision Transformer
University of California, Los Angeles, USA · Columbia University, USA · The University of Melbourne, Australia +1
SCI-CLIP: Segment-Centric Inference with Reference Memory for Training-Free Open-Vocabulary Segmentation
Aug 6, 2026Mohamad Zamini, Diksha ShuklaOpen-Vocabulary Segmentation Frozen Contrastive Language-Image Pre-Training Visual Encoder
University of Wyoming Laramie, WY
Dense Metric Depth Completion from Sparse Direct Time-of-Flight Sensors
Aug 5, 2026Hakyeong Kim, Ruicheng Wang, Chengtang Yao +2Dense Prediction Vision Encoders
KAIST · USTC · Microsoft Research Asia
LoRetta: A Foundation Model and Extensive Dataset for Global-Scale Remote Sensing Dense Image Matching
Aug 4, 2026Siwei Yu, Han Guo, Zhenwei Shi +1Remote Sensing Dense Prediction
Department of Aerospace Intelligent Science and Technology, School of Astronautics, Beihang University, Beijing 100191, China, and also with the Key Laboratory of Spacecraft Design Optimization and Dynamic Simulation Technologies, Ministry of Education
VARPose: Flexible 2D Pose Densification via Visual Autoregressive Modeling for Enhanced 3D Lifting
Aug 3, 2026Kaiyuan Pu, Tiantian Yang, Dan ZengWifi-Csi 3D Human Pose Estimation Category-Level Object Pose Estimation
School of Artificial Intelligence, Sun Yat-sen University Zhuhai, China · The Technology Innovation Center for Collaborative Applications of Natural Resources Data in GBA, MNR Guangzhou, China
ST-LoRA: Single Trajectory LoRA Ensemble for Uncertainty Aware Agricultural Segmentation
Aug 2, 2026Mohamed Farag, Genc Hoxha, Yahia Maleki +2Ensemble Hip-Lora
Machine Learning in Agriculture Lab, Institute of Geodesy and Geoinformation, University of Bonn, Bonn, Germany · Commonwealth Scientific and Industrial Research Organisation (CSIRO), Australia · Lamarr Institute for Machine Learning and Artificial Intelligence, University of Bonn, Bonn, Germany
ProgFormer: Hierarchical Voxel Diffusion Transformer for Longitudinal Brain MRI Prediction
Jul 30, 2026Dexuan Ding, Yuankai Qi, Luping Zhou +3Voxel Dense Prediction
Macquarie University · University of Sydney · University of California Merced
Lottery Tickets Are Not Deployment Tickets
Jul 29, 2026Bum Jun KimLotteries Decision Thresholds
The University of Tokyo
JEPADepth: Masked Predictive Representation Learning for Self-Supervised Monocular Depth Estimation
Jul 29, 2026Ionuţ Grigore, Călin-Adrian PopaMonocular Depth Estimation Dense Prediction
Politehnica University of Timis,oara, Romania
DensFiLM: Density-Conditioned Video Saliency for Crowd Scenes
Jul 28, 2026Anis Ur RahmanSaliency Dense Prediction
CSC - IT Center for Science Ltd., Espoo, Finland
Toward High-Fidelity 3D Point-Cloud Learning for Brain Folding Morphology Prediction Using Trans-Unet
Jul 23, 2026Geran Zhao, Xiaotian Li, Poorya Chavoshnejad +4U-Net Point Clouds
Department of Mathematics and Statistics, Binghamton University, Vestal, NY 13902, USA · School of Computing, Binghamton University, Vestal, NY 13850, USA · Department of Mechanical Engineering, Binghamton University, Vestal, NY 13850, USA
Unified Video Dense Prediction from Disjoint Data
Jul 23, 2026Yihong Sun, Seoung Wug Oh, Jiahui Huang +2Dense Prediction Video Diffusion Models
Adobe Research · Cornell University
Point Ladder Tuning: Parameter-Efficient Hierarchical Adaptation for 3D Point Cloud Understanding
Jul 21, 2026Junlin Chang, Longhao Zou, Rui LiPoint Clouds Parameter-Efficient Fine-Tuning Methods
Beihang University, Beijing · Pengcheng Laboratory, Shenzhen
DPNeXt: A Lightweight Multi-Scale Feature Fusion Framework for Efficient ViT-Based Multi-Task Dense Prediction
Jul 17, 2026Jehun Kang, Jungha Wang, Youngjun Hwang +1Dense Prediction Depth Estimation
School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea
ARDepth: Auto-regressive Monocular Depth Estimation with Progressive Visual Conditioning
Jul 14, 2026Zijie Wang, Wei Zhang, Weiming Zhang +4Monocular Depth Estimation Depth Estimation
School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, 510006, China · Shenzhen Loop Area Institute, Shenzhen, 518038, China · Baidu Inc., Shenzhen, 518066, China +3
Next-Dense-Stride Prediction for Multimodal Autoregressive Visual Modeling
Jul 10, 2026Chicago Y. Park, Jialin Mao, Xiaojian Xu +3Autoregressive Image Generation Dense Prediction
University of Wisconsin–Madison · GE HealthCare
Physics-guided spatiotemporal neural models for fuel density prediction
Jul 8, 2026Tolga Caglar, Jaynil Jaiswal, Saqib Azim +3Physics-Guided Machine Learning Wildfire Prediction
San Diego Supercomputer Center University of California, San Diego
From RGB Generation to Dense Field Readout: Pixel-Space Dense Prediction with Text-to-Image Models
Jul 7, 2026Zanyi Wang, Xin Lin, Haodong Li +2Dense Prediction Single-Cell Foundation Models
1UCSD · 2HKUST
Repurposing CLIP to Localize at Pixel Level
Jul 6, 2026Jiaxiang Fang, Shiqiang Ma, Jing Wang +3Dense Prediction Pixels
School of Computer Science and Engineering, Central South University, Changsha 410083, China · Advanced Technology Center Beijing AI Laboratory, Chao-Yang District, Beijing 100027, China · Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China +1
Topology-Driven Transferability Estimation for 3D Medical Vision Foundation Models
Jul 5, 2026Jiaqi Tang, Shaoyang Zhang, Fandong Zhang +33D Medical Image Segmentation Topology
National Institute of Health Data Science, Peking University, Beijing, China · Institute of Medical Technology, Peking University, Beijing, China · State Key Laboratory of General Artificial Intelligence, Peking University, Beijing, China +2
FDR-Occ: Factorized Dense Routing for Full-Spectrum 3D Occupancy Prediction
Jul 4, 2026Dubing Chen, Huan Zheng, Tianyi Yan +53D Semantic Occupancy Prediction Dense Prediction
SKL-IOTSC, CIS, University of Macau · Chongqing Afari Intelligent Drive Co., Ltd. · Geely Automobile Research Institute (Ningbo) Co., Ltd.
Less Tokens, Better Forecasts: Sparse Residual Routing for Efficient Weather Prediction
Jul 2, 2026Janet Wang, Yunbei Zhang, Lin Zhao +3Artificial Intelligence Weather Models Weather Prediction
Tulane University · Northeastern University · University of Alabama at Birmingham +1
DrivingDepth: Sparse-Prompted Pixel-wise Scale Correction for Driving Depth Estimation
Jun 30, 2026Chi Huang, Wenhao Zhang, Hang Yin +5Depth Estimation Lidar
Baidu Inc.
MUSE: Unlocking Timestep as Native Task Steering for One-Step Dense Prediction
Jun 29, 2026Shuo Zhou, Zhaoxin Li, Xiujuan ChaiDense Prediction Multi--Task Learning
Agricultural Information Institute, Chinese Academy of Agricultural Sciences, Beijing, China. · Key Laboratory of Agricultural Big Data, Ministry of Agriculture and Rural Affairs, Beijing, China.
UniGP: Taming Diffusion Transformer for Prior-Preserved Unified Generation and Perception
Jun 29, 2026Qin Guo, Hao Luo, Dongxu Yue +4Diffusion Transformers Dense Prediction
The Hong Kong University of Science and Technology · DAMO Academy, Alibaba Group, Zhejiang, China · Hupan Lab, Zhejiang Province +4
Multi-Modal Conditioned High-Resolution Transformer for Urban Electromagnetic Field Map Prediction Download PDF
Jun 26, 2026Do-Eon Kim, Dongryul Park, Seungyoung Ahn +3Reconfigurable Intelligent Surfaces Spatio-Temporal Transformers
Soongsil University, Seoul 06978, Republic of Korea · Cho Chun Shik Graduate School of Mobility, Korea Advanced Institute of Science and Technology, Daejeon 34051, Republic of Korea · Department of Intelligent Semiconductors, Soongsil University, Seoul 06978, Republic of Korea
Efficient Remote Sensing Instance Segmentation with Linear-Time State Space Distilled Visual Foundation Models
Jun 24, 2026Qinzhe Yang, Keyan Chen, Jia Xu +2Remote Sensing Image Segmentation Remote Sensing
Shen Yuan Honors College, Beihang University, Beijing 100191, China · Department of Aerospace Intelligent Science and Technology, School of Astronautics, and with the State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing 100191, China · Qian Xuesen Laboratory of Space Technology, China Academy of Space Technology, Beijing 100094, China
FLM-Occ: Feed-forward Likelihood Maximization for Efficient Indoor Occupancy Prediction
Jun 19, 2026Guangcheng Chen, Lihuang Fang, Huaqi Tao +3Occupancy Voxel
Southern University of Science and Technology · Shenzhen Key Laboratory of Robotics and Computer Vision · Guangdong Laboratory of Artificial Intelligence and Digital Economy (Shenzhen)
Instance-Aware Knowledge Distillation for Semi-Supervised Learning of an On-Board Multi-Task Dense Prediction Model for Collision Avoidance System
Jun 15, 2026Gyutae Hwang, Sang Jun LeeDense Prediction Autonomous Driving Perception
Division of Electronics and Information Engineering, Jeonbuk National University, 567 Baekje-daero, Deokjin-gu, Jeonju, 54896, Republic of Korea
Task-Instructed Causal Routing of Vision Foundation Models for Multi-Task Learning
Jun 14, 2026Donghyun Han, Yuseok Bae, Jung Uk Kim +1Recent Vision Foundation Models Dense Prediction
Electronics and Telecommunications Research Institute (ETRI), Korea · Kyung Hee University, Korea · Chonnam National University, Korea
Segmentation-based Detection for Efficient Multi-Task Spacecraft Perception
Jun 13, 2026Sivaperuman Muniyasamy, Surendar DevasundaramSpacecraft Mobilenetv2
University of Arizona, Tucson, AZ, USA
ViT-Up: Faithful Feature Upsampling for Vision Transformers
Jun 12, 2026Krispin Wandel, Jingchuan Wang, Hesheng WangSelf-Supervised Vision Transformers Dense Prediction
Shanghai Jiao Tong University, Shanghai, China
Modality Forcing for Scalable Spatial Generation
Jun 11, 2026Bardienus Pieter Duisterhof, Deva Ramanan, Jeffrey Ichnowski +2Multi-Reference Image Generation Dense Prediction
Carnegie Mellon University · World Labs
Leveraging Metric Depth for Relative Depth Prediction
Jun 9, 2026Xiaoyang Bi, Shuaikun Liu, Zhaohong Liu +5Monocular Depth Estimation Dense Prediction
Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia · Beijing University of Posts and Telecommunications
Large Depth Completion Model from Sparse Observations
May 28, 2026Zhu Yu, Zhengyi Zhao, Runmin Zhang +7Depth Estimation Dense Prediction
Zhejiang University · Internship at Tongyi Lab · Tongyi Lab, Alibaba Group +4
SeeGroup: Multi-Layer Depth Estimation of Transparent Surfaces via Self-Determined Grouping
May 27, 2026Hongyu Wen, Jia DengDepth Estimation Dense Prediction
Department of Computer Science, Princeton University
SIGMA: Bridging Structural and Distributional Gaps for Vision Foundation Model Adaptation
May 27, 2026Lingyu Xiong, Jinjin Shi, Xuran Xu +3Recent Vision Foundation Models Parameter-Efficient Fine-Tuning Methods
Xiaomi Corporation
Structure over Pixels: Learning Variable-Length Visual Programs
May 26, 2026Piotr Wyrwiński, Kacper Dobek, Krzysztof KrawiecVisual Tokenizers Semantic Scene Understanding
Institute of Computing Science Poznan University of Technology, Poznan, Poland
Phase-Aware Wavelet-Based-Scattering Encoder-Decoder for Dense Predictions
May 23, 2026Ghassen Marrakchi, Basarab MateiWavelets Dense Prediction
Northern Paris Computer Science Lab, Sorbonne Paris Nord University, Villetaneuse, France.
DepthAgent: Towards Better Universal Depth Estimation via Sample-wise Expert Selection
May 22, 2026Jie Zhu, Girish Chandar Ganesan, Xiaoming LiuMonocular Depth Estimation Monocular
Michigan State University · University of North Carolina at Chapel Hill
StruMPL: Multi-task Dense Regression under Disjoint Partial Supervision and MNAR Labels
May 19, 2026Reza M. Asiyabi, Juan Alberto Molina-Valero, The SEOSAW Partnership +2Biomass Dense Prediction
School of Geosciences, University of Edinburgh, UK · National Centre for Earth Observation (NCEO), UK · Department of Spatial Sciences, Faculty of Environmental Sciences, Czech University of Life Sciences Prague, Praha, Czech Republic
Metric-Guided Feature Fusion of Visual Foundation Models for Segmentation Tasks
May 16, 2026Yachan Guo, JoseLuis Gomez Zurita, Danna Xue +2Recent Vision Foundation Models Dense Prediction
1Universitat Aut`onoma de Barcelona · 2Computer Vision Center · 3Harbin Institute of Technology, Shenzhen
Invaria: Learning Scale and Density Invariance in Point Clouds via Next-Resolution Prediction
May 15, 2026Chun-Peng Chang, Shaoxiang Wang, Alain Pagani +2Point Clouds Dense Prediction
TU Delft · DFKI
VIP: Visual-guided Prompt Evolution for Efficient Dense Vision-Language Inference
May 12, 2026Hao Zhu, Shuo Jin, Wenbin Liao +4Open-Vocabulary Segmentation Visual In-Context Learning
Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China · School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China · XJTLU +1
Revisiting Shadow Detection from a Vision-Language Perspective
May 12, 2026Yonghui Wang, Shaokai Liu, Wengang Zhou +2Dense Prediction Text Embeddings
Department of Electronic Engineering and Information Science, University of Science and Technology of China · School of Management, Hefei University of Technology · School of Artificial Intelligence and Data Science, University of Science and Technology of China
Semantic Alignment in Hyperbolic Space for Open-Vocabulary Semantic Segmentation
May 9, 2026Hoang M. Truong, Hai Nguyen-Truong, Dang HuynhHyperbolic Space Semantic Geometry
Fulbright University Vietnam
CONTRA: Conformal Prediction Region via Normalizing Flow Transformation
May 8, 2026Zhenhan Fang, Aixin Tan, Jian HuangOnline Conformal Prediction Normalizing Flows
Department of Statistics and Actuarial Science The University of Iowa Iowa City, IA 52242, USA · Department of Applied Mathematics The Hong Kong Polytechnic University Hongkong, China

Sep 30, 2026, cs.CVJ/K move · Enter open · S save

PixelDense: Dense Prediction as Representation Alignment for Pixel Diffusion

Lehan Yang, Daiqing Qi, Wenhao Zhang, Avery Li+8

University of Virginia · Michigan State University · Adobe+1

Dense Prediction Diffusion Transformers Dinov3

Open paper AskPDF arXiv

Representation alignment (REPA) accelerates diffusion transformer training, but its alignment targets are almost exclusively semantic encoders such as DINOv2 and CLIP. Recent analysis points to spatial structure, not global semantics, as the carrier of the alignment effect, yet dense-prediction foundation models trained to predict that structure remain overlooked as REPA targets. In pixel-space diffusion, SAM2, Depth Anything v2, and Metric3D v2 each outperform the DINOv2-only GenEval baseline, with the two geometric teachers leading the segmentation teacher. A flat sum of all four teachers, however, lands below the best single geometric teacher, as semantic and geometric gradients compete for one denoiser projection. We introduce PixelDense, which routes DINOv2 and SAM2 through a semantic projection stream, routes Depth Anything v2 and Metric3D v2 through a geometric projection stream, and adds a weight-space orthogonality penalty that keeps the two streams in disjoint subspaces. All four teachers are frozen during training and dropped at inference. Applied to PixelGen and DeCo with a single recipe, PixelDense improves GenEval, DPG-Bench, and HPS v2.1, raises PixelGen-XXL's GenEval Overall from 0.7927 to 0.8093, and beats every single-teacher and unfactored multi-teacher variant. In partial-noise reconstruction, independent panoptic, depth, and surface-normal probes show up to 53.1% PQ gain and 36.0% depth AbsRel reduction at

τ=0.5

across COCO and Flickr30K. From random initialization, PixelDense also reaches the baseline's peak GenEval 1.23x faster. In SDEdit editing on PIE-Bench, PixelDense keeps more of the source background and layout at every edit strength, raising background PSNR by up to 2.2 dB.

Momentum

Related topics

Latest papers 85