ArXiv Computer Vision research for Monday, June 10, 2024.

00:20: DualAD: Disentangling the Dynamic and Static World for End-to-End Driving

01:41: NeuroMoCo: A Neuromorphic Momentum Contrast Learning Method for Spiking Neural Networks

03:22: Vehicle Vectors and Traffic Patterns from Planet Imagery

04:15: A Guide to Stochastic Optimisation for Large-Scale Inverse Problems

05:37: Cascading Unknown Detection with Known Classification for Open Set Recognition

06:42: Latent Directions: A Simple Pathway to Bias Mitigation in Generative AI

07:57: MVGamba: Unify 3D Content Generation as State Space Sequence Modeling

09:32: UMAD: Unsupervised Mask-Level Anomaly Detection for Autonomous Driving

10:15: Improving Deep Learning-based Automatic Cranial Defect Reconstruction by Heavy Data Augmentation: From Image Registration to Latent Diffusion Models

11:47: Diffusion-RPO: Aligning Diffusion Models through Relative Preference Optimization

13:12: Generalizing to Unseen Domains in Diabetic Retinopathy with Disentangled Representations

15:01: FPN-IAIA-BL: A Multi-Scale Interpretable Deep Learning Model for Classification of Mass Margins in Digital Mammography

16:18: STimage-1K4M: A histopathology image-gene expression dataset for spatial transcriptomics

17:53: Hybrid Video Anomaly Detection for Anomalous Scenarios in Autonomous Driving

18:35: Margin-aware Preference Optimization for Aligning Diffusion Models without Reference

20:24: SYM3D: Learning Symmetric Triplanes for Better 3D-Awareness of GANs

21:48: Spatiotemporal Graph Neural Network Modelling Perfusion MRI

22:57: VCR: Visual Caption Restoration

24:37: AID: Adapting Image2Video Diffusion Models for Instruction-guided Video Prediction

26:29: NarrativeBridge: Enhancing Video Captioning with Causal-Temporal Narrative

28:09: Monkey See, Monkey Do: Harnessing Self-attention in Motion Diffusion for Zero-shot Motion Transfer

30:12: Merlin: A Vision Language Foundation Model for 3D Computed Tomography

32:58: Genomics-guided Representation Learning for Pathologic Pan-cancer Tumor Microenvironment Subtype Prediction

34:26: PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction

36:04: NaRCan: Natural Refined Canonical Image with Integration of Diffusion Prior for Video Editing

37:28: Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation

39:08: GaussianCity: Generative Gaussian Splatting for Unbounded 3D City Generation

40:52: IllumiNeRF: 3D Relighting without Inverse Rendering