A linearized solver estimates rolling-shutter relative pose and motion from 7 affine correspondences in 1.2 ms and reports best-in-benchmark accuracy plus usable translational velocity.
Canonical reference
In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)
Canonical reference. 82% of citing Pith papers cite this work as background.
60
Pith papers citing it
Background
82% of classified citations
citation-role summary
background 8
dataset 2
baseline 1
citation-polarity summary
representative citing papers
A single unified multimodal model matches leading task-specialized vision systems across detection, segmentation, dense geometry, and multi-view 3D by casting all outputs as native text or image generation.
A self-supervised method pretrains an encoder on eight PSP images per view to learn generalizable subsurface scattering representations that transfer to relighting and dense footprint reconstruction on unseen complex objects.
The paper defines the 4DVLT task for worldline-centered 4D scene understanding, releases Instruct-4D with 129.4K QA pairs, and presents 4DTrack achieving 62.68 TGA_Top1, outperforming adapted baselines by 19.62 points.
WHU-Infra3D is a new large-scale multi-modal dataset and benchmark for 3D roadside infrastructure inventory, providing over 175k 2D boxes, thousands of 3D instances, and 181k annotations across five core tasks while exposing cross-city gaps and long-tailed defect vulnerabilities.
On the public ReMIND dataset, a systematic benchmark of six synthesis models across 48 experiments finds LPIPS correlates with downstream segmentation utility while SSIM does not, with SynDiff-2.5D performing best.
Tetris uses tile-level polyomino sampling and packing to materialize object tracks from stationary video with up to 68.8x throughput gain at under 5% HOTA loss.
Urban-ImageNet is a 2-million-image multi-modal dataset with HUSIC 10-class taxonomy enabling benchmarks for urban scene classification, cross-modal retrieval, and instance segmentation.
Gaussian Kernel Attention replaces learned QKV projections with a Gaussian RBF kernel on per-head token features, using 0.42x parameters and 0.49x FLOPs while showing competitive language modeling performance at depth 20.
DP-GCL improves differentially private contrastive learning by bounding group-level contributions through batch partitioning and intra-group augmentation, delivering 5.6% higher image classification accuracy and 20.1% higher retrieval accuracy than existing approaches.
AttentionBender applies 2D transforms to cross-attention maps in video diffusion transformers, producing distributed distortions and glitch aesthetics that reveal entangled attention mechanisms while serving as both an XAI probe and creative tool.
DHCNet improves ultra-fine-grained visual categorization by progressively building holistic cognition from local discrepancies using self-shuffling and refinement on limited data.
A system combining VLM landmark instructions with real-time corrective spatial audio reduces route deviations in a small user study compared to VLM-only and Google Maps audio baselines.
MobileMold provides 4941 smartphone microscopy images and shows deep learning models reach 99.5% accuracy on mold detection and food classification tasks.
PipeMFL-240K provides 249,320 labeled MFL pipeline scans across 12 categories — the first large public benchmark for MFL defect detection — and baseline tests show current detectors cap near 0.5 mAP50.
Quantum circuits for coherent multilayer neural network inference achieve quadratic to polylogarithmic speedups over classical methods depending on quantum data access models for inputs and weights.
MultiMat shows multimodal large models plus constrained search produce higher-quality procedural material graphs than text-only baselines on a new production dataset.
A frozen SAM2 backbone with adaptive token selection and symmetric KL clustering achieves competitive self-supervised video object segmentation by aligning soft part assignments across time.
MBR decoding is reformulated via a noisy-channel decomposition into four weighted probabilistic terms, revealing that channel importance is metric-specific and task-agnostic, and that reweighting can improve performance.
TCG-AR is a real-time multi-view AR system for trading card games using only commodity RGB cameras and synthetic training data.
AF3AD is a modular synthesis framework using center-conditioned parametric deformations in local PCA frames to create diverse pseudo-anomalies, improving unsupervised 3D anomaly detection on AnomalyShapeNet and Real3D-AD.
LAFM adapts the source distribution in flow matching policies via a latent action model to better match fragmented robotic action spaces, claiming 23.4% higher real-world success and 10.4% on LIBERO-90 while beating larger pre-trained models.
RBFN projection heads serve as competitive replacements for MLP heads in SSL and enable SNS, a label-free metric from RBF parameters that correlates strongly with logistic regression evaluation.
FATE combines pillar encoding via orthogonal polynomial basis with frequency-aware training to enable event-based object detection at up to 200 Hz without internal temporal sub-binning.
citing papers explorer
-
Rolling Shutter Relative Pose Estimation Made Practical
A linearized solver estimates rolling-shutter relative pose and motion from 7 affine correspondences in 1.2 ms and reports best-in-benchmark accuracy plus usable translational velocity.
-
Vision as Unified Multimodal Generation
A single unified multimodal model matches leading task-specialized vision systems across detection, segmentation, dense geometry, and multi-view 3D by casting all outputs as native text or image generation.
-
From Phase to Phenomenon: Self-Supervised Learning of Subsurface Scattering with Minimal Phase-shift Inputs
A self-supervised method pretrains an encoder on eight PSP images per view to learn generalizable subsurface scattering representations that transfer to relighting and dense footprint reconstruction on unseen complex objects.
-
4DVLT: Dynamic Scene Understanding with Worldline-Centered Vision-Language Tracking
The paper defines the 4DVLT task for worldline-centered 4D scene understanding, releases Instruct-4D with 129.4K QA pairs, and presents 4DTrack achieving 62.68 TGA_Top1, outperforming adapted baselines by 19.62 points.
-
WHU-Infra3D: A Full-stack Multi-modal Dataset and Benchmark for 3D Roadside Infrastructure Inventory
WHU-Infra3D is a new large-scale multi-modal dataset and benchmark for 3D roadside infrastructure inventory, providing over 175k 2D boxes, thousands of 3D instances, and 181k annotations across five core tasks while exposing cross-city gaps and long-tailed defect vulnerabilities.
-
A Systematic Benchmark of Intraoperative Ultrasound-to-MR Synthesis for Brain Tumour Surgery
On the public ReMIND dataset, a systematic benchmark of six synthesis models across 48 experiments finds LPIPS correlates with downstream segmentation utility while SSIM does not, with SynDiff-2.5D performing best.
-
Tetris: Tile-level Sampling for Efficient and High-Fidelity Video Object Tracking
Tetris uses tile-level polyomino sampling and packing to materialize object tracks from stationary video with up to 68.8x throughput gain at under 5% HOTA loss.
-
Urban-ImageNet: A Large-Scale Multi-Modal Dataset and Evaluation Framework for Urban Space Perception
Urban-ImageNet is a 2-million-image multi-modal dataset with HUSIC 10-class taxonomy enabling benchmarks for urban scene classification, cross-modal retrieval, and instance segmentation.
-
Projection-Free Transformers via Gaussian Kernel Attention
Gaussian Kernel Attention replaces learned QKV projections with a Gaussian RBF kernel on per-head token features, using 0.42x parameters and 0.49x FLOPs while showing competitive language modeling performance at depth 20.
-
Differentially Private Contrastive Learning via Bounding Group-level Contribution
DP-GCL improves differentially private contrastive learning by bounding group-level contributions through batch partitioning and intra-group augmentation, delivering 5.6% higher image classification accuracy and 20.1% higher retrieval accuracy than existing approaches.
-
AttentionBender: Manipulating Cross-Attention in Video Diffusion Transformers as a Creative Probe
AttentionBender applies 2D transforms to cross-attention maps in video diffusion transformers, producing distributed distortions and glitch aesthetics that reveal entangled attention mechanisms while serving as both an XAI probe and creative tool.
-
Divide-and-Conquer Approach to Holistic Cognition in High-Similarity Contexts with Limited Data
DHCNet improves ultra-fine-grained visual categorization by progressively building holistic cognition from local discrepancies using self-shuffling and refinement on limited data.
-
Navig-AI-tion: Navigation by Contextual AI and Spatial Audio
A system combining VLM landmark instructions with real-time corrective spatial audio reduces route deviations in a small user study compared to VLM-only and Google Maps audio baselines.
-
MobileMold: A Smartphone-Based Microscopy Dataset for Food Mold Detection
MobileMold provides 4941 smartphone microscopy images and shows deep learning models reach 99.5% accuracy on mold detection and food classification tasks.
-
PipeMFL-240K: A Large-scale Dataset and Benchmark for Object Detection in Pipeline Magnetic Flux Leakage Imaging
PipeMFL-240K provides 249,320 labeled MFL pipeline scans across 12 categories — the first large public benchmark for MFL defect detection — and baseline tests show current detectors cap near 0.5 mAP50.
-
Accelerating Inference for Multilayer Neural Networks with Quantum Computers
Quantum circuits for coherent multilayer neural network inference achieve quadratic to polylogarithmic speedups over classical methods depending on quantum data access models for inputs and weights.
-
MultiMat: Multimodal Program Synthesis for Procedural Materials using Large Multimodal Models
MultiMat shows multimodal large models plus constrained search produce higher-quality procedural material graphs than text-only baselines on a new production dataset.
-
`Attention-Guided Cross-Temporal Clustering for Self-Supervised Video Object Segmentation
A frozen SAM2 backbone with adaptive token selection and symmetric KL clustering achieves competitive self-supervised video object segmentation by aligning soft part assignments across time.
-
Noisy-Channel Minimum Bayes Risk Decoding
MBR decoding is reformulated via a noisy-channel decomposition into four weighted probabilistic terms, revealing that channel importance is metric-specific and task-agnostic, and that reweighting can improve performance.
-
TCG-AR: Real-Time Multi-View Augmented Reality for Trading Card Game Streaming
TCG-AR is a real-time multi-view AR system for trading card games using only commodity RGB cameras and synthetic training data.
-
Anomaly Factory 3D: A Modular Framework for Diverse Pseudo-Anomaly Synthesis in Unsupervised 3D Anomaly Detection
AF3AD is a modular synthesis framework using center-conditioned parametric deformations in local PCA frames to create diverse pseudo-anomalies, improving unsupervised 3D anomaly detection on AnomalyShapeNet and Real3D-AD.
-
Flowing With Purpose: Latent Action Guided Flow Matching Policies For Robotic Manipulation
LAFM adapts the source distribution in flow matching policies via a latent action model to better match fragmented robotic action spaces, claiming 23.4% higher real-world success and 10.4% on LIBERO-90 while beating larger pre-trained models.
-
Radial Basis Function Networks as Projection Heads in Self-Supervised Learning
RBFN projection heads serve as competitive replacements for MLP heads in SSL and enable SNS, a label-free metric from RBF parameters that correlates strongly with logistic regression evaluation.
-
FATE: Pillar Encoding and Frequency-Aware Training for Event-Based Object Detection
FATE combines pillar encoding via orthogonal polynomial basis with frequency-aware training to enable event-based object detection at up to 200 Hz without internal temporal sub-binning.
-
Learning Sparse Latent Predictive Foundation Model for Multimodal Neuroimaging
Neuro-JEPA, a JEPA-and-MoE transformer pretrained on 1.55M brain MRI scans, outperformed prior neuroimaging foundation models and was the only one to beat a simple CNN baseline on average.
-
Jaguar: Fast Private CNN Inference with Power-of-Two Homomorphic Arithmetic
Jaguar replaces prime-modulus HE with power-of-two arithmetic to enable coefficient-domain convolution and local-shift truncation, reporting 2-3.7x lower latency than Cheetah and Rhombus on ResNet-18/50 and MobileNetV2.
-
Model Merging: Foundations and Algorithms
New cycle-consistent optimization, task vector theory, singular vector decompositions, adaptive routing, and efficient evolutionary search provide foundations for merging neural network weights across tasks.
-
Neighbor2Inverse: Self-Supervised Denoising for Low-Dose Region-of-Interest Phase Contrast CT
Neighbor2Inverse adapts the Neighbor2Neighbor principle to train a denoising network directly in the image domain for low-dose PBI-CT by using independently noised subsampled projections.
-
Remote SAMsing: From Segment Anything to Segment Everything
Remote SAMsing pipeline boosts SAM2 coverage on remote sensing scenes from 30-68% to 91-98% via multi-pass masking and boundary-aware merging while preserving mask quality.
-
Threat-Oriented Digital Twinning for Security Evaluation of Autonomous Platforms
A threat-oriented digital twinning methodology and open-source modular twin is introduced for security evaluation of autonomous platforms, translating threat analysis into controllable tests for spoofing, replay, and adversarial ML attacks.
-
Towards interpretable AI with quantum annealing feature selection
Quantum annealing solves a combinatorial feature-map selection problem for CNNs, yielding improved class disentanglement over GradCAM and GradCAM++ in the reported evaluation.
-
Where are they looking in the operating room?
Gaze-following models on extended 4D-OR and Team-OR datasets reach F1 scores of 0.92 for clinical role prediction and 0.95 for surgical phase recognition while improving team communication detection by over 30%.
-
Geometric Correction of Side-Scan Sonar Images with Image-Consistent Attitude Refinement
A geometric correction technique for side-scan sonar images that refines yaw-pitch attitude by fusing navigation baselines with image-inferred perturbations separated via port-starboard symmetry.
-
Automated Batch Distillation Process Simulation for a Large Hybrid Dataset for Deep Anomaly Detection
An automated Python simulator, calibrated to one experimental run, generates consistent time-series data for many batch distillation scenarios including anomalies, forming an openly released hybrid dataset for deep anomaly detection.
-
Ensemble-Based Dirichlet Modeling for Predictive Uncertainty and Selective Classification
Ensemble-based method of moments on softmax outputs produces stable Dirichlet predictive distributions that improve uncertainty-guided tasks like selective classification over evidential deep learning.
-
Parser-Oriented Structural Refinement for a Stable Layout Interface in Document Parsing
A parser-oriented refinement stage performs set-level reasoning on detector hypotheses to jointly decide instance retention, refine boxes, and set parser input order, cutting reading order errors to 0.024 on OmniDocBench.
-
Explicit Logic Channel for Validation and Enhancement of MLLMs on Zero-Shot Tasks
An Explicit Logic Channel of LLM, VFM and probabilistic inference validates and improves zero-shot MLLMs via Consistency Rate without ground-truth labels.
-
Holi-DETR: Holistic Fashion Item Detection Leveraging Contextual Information
Holi-DETR improves fashion item detection by integrating co-occurrence probabilities, inter-item spatial arrangements, and body keypoint relationships into the DETR architecture.
-
Graph Signal Denoising Using Regularization by Denoising and Its Parameter Estimation
RED is adapted to graph signals with deep unrolling for parameter estimation, yielding lower MSE than prior graph denoising methods on synthetic and real data.
-
LaV-CoT: Language-Aware Visual CoT with Multi-Aspect Reward Optimization for Real-World Multilingual VQA
LaV-CoT introduces a multi-stage visual CoT pipeline and GRPO training with language-consistency rewards, delivering up to 9.5% accuracy gains on multilingual VQA benchmarks over similar-sized open models.
-
Near OOD Detection for Vision-Language Prompt Learning with Contrastive Logit Score
Contrastive Logit Score (CLS) improves near OOD detection AUROC by up to 11.67% for pre-trained vision-language prompt learning methods as a plug-and-play post-hoc function.
-
SignNet-1M: Large-Scale Multilingual Sign Language Video Dataset with Downstream Benchmarks
The paper releases SignNet-1M, a 1M-scale augmented dataset for ASL, CSL and DGS with 3DGS and diffusion-based variations, plus benchmarks showing improved cross-shift generalization.
-
Quality-Diversity Search in Sound Generation: Investigating Innovation Engines for Audio Exploration
MAP-Elites with CPPNs, DSP graphs, and a deep classifier produces diverse synthetic sounds across durations and musical/non-musical contexts.
-
Trustworthy Visual Predicates for Robust Manipulation Understanding under Degradation
Introduces a structured framework showing that visual predicate failures under degradation are non-uniform, with static predicates more robust than dynamic ones like grasp and release, and quantifies downstream accuracy drops.
-
Efficient 3D Content Reconstruction and Generation
Presents Instant3D for rapid text/image-to-3D generation via multi-view diffusion plus feed-forward reconstruction, and FastMap for 10x faster structure-from-motion with comparable accuracy.
-
MHSA: A Lightweight Framework for Mitigating Hallucinations via Steered Attention in LVLMs
MHSA mitigates hallucinations in LVLMs by training an MLP to steer cross-modal attention, extending detection work to mitigation via attention replacement at inference.
-
RACANet: Reliability-Aware Crowd Anchor Network for RGB-T Crowd Counting
RACANet proposes a reliability-aware two-stage fusion network with cross-modal pretraining and local anchor modules that outperforms prior RGB-T crowd counting methods on standard benchmarks.
-
ProBA: Probabilistic Bundle Adjustment with the Bhattacharyya Coefficient
ProBA replaces rigid point tracks with a probabilistic pose graph and 3D Gaussian landmarks, optimizing via negative log-likelihood with the Bhattacharyya coefficient to expand the basin of attraction in prior-free SfM.
-
Neuron ranking -- an informed way to condense convolutional neural networks architecture
Shapley value and variational importance switch methods produce consistent rankings of filter importance in CNNs, enabling compression and interpretability.
-
SEADA: An efficient methodology for optimizing mixed-precision DNNs on multi-precision spatial architectures
SEADA introduces an analytical framework combining cost models, mapping tools, and entropy-based precision selection to optimize mixed-precision DNNs on multi-precision spatial architectures.