Visual Inference Lab @TU Darmstadt

1-stage-wseg

Single-Stage Semantic Segmentation from Image Labels (CVPR 2020)

cos-cvae

Diverse Image Captioning with Context-Object Split Latent Spaces (NeurIPS 2020)

da-sac

Self-supervised Augmentation Consistency for Adapting Semantic Segmentation (CVPR 2021)

dense-ulearn-vos

Dense Unsupervised Learning for Video Segmentation (NeurIPS*2021)

dpp

Detail-Preserving Pooling in Deep Networks (CVPR 2018)

irr

Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation (CVPR 2019)

multi-mono-sf

Self-Supervised Multi-Frame Monocular Scene Flow (CVPR 2021)

n3net

Neural Nearest Neighbors Networks (NIPS*2018)

ppac_refinement

Probabilistic Pixel-Adaptive Refinement Networks (CVPR 2020)

self-mono-sf

Self-Supervised Monocular Scene Flow Estimation (CVPR 2020)

visinf/1-stage-wseg

Single-Stage Semantic Segmentation from Image Labels (CVPR 2020)

visinf/n3net

Neural Nearest Neighbors Networks (NIPS*2018)

visinf/self-mono-sf

Self-Supervised Monocular Scene Flow Estimation (CVPR 2020)

visinf/irr

Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation (CVPR 2019)

visinf/dense-ulearn-vos

Dense Unsupervised Learning for Video Segmentation (NeurIPS*2021)

visinf/cos-cvae

Diverse Image Captioning with Context-Object Split Latent Spaces (NeurIPS 2020)

visinf/adapter_plus

[CVPR 2024] Official implementation of "Adapters Strike Back"

visinf/lnfmm

Latent Normalizing Flows for Many-to-Many Cross Domain Mappings (ICLR 2020)

visinf/cad

Content-Adaptive Downsampling in Convolutional Neural Networks (CVPR 2023 Workshop on Efficient Deep Learning for Computer Vision)

visinf/veto

Vision Relation Transformer for Unbiased Scene Graph Generation (ICCV 2023)

visinf/funnybirds

FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods (ICCV 2023)

visinf/self-adaptive

Semantic Self-adaptation: Enhancing Generalization with a Single Sample

visinf/fast-axiomatic-attribution

Fast Axiomatic Attribution for Neural Networks (NeurIPS*2021)

visinf/funnybirds-framework

FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods (ICCV 2023)

visinf/mar-scf

Normalizing Flows with Multi-Scale Autoregressive Priors (CVPR 2020)

visinf/fldr-vfi

Efficient Feature Extraction for High-resolution Video Frame Interpolation (BMVC 2022)

visinf/primaps

visinf/pixelpyramids

PixelPyramids: Exact Inference Models from Lossless Image Pyramids (ICCV 2021)

visinf/DIAGen

DIAGen: Semantically Diverse Image Augmentation with Generative Models for Few-Shot Learning (GCPR 2024)

visinf/s2-flow

S2-Flow: Joint Semantic and Style Editing of Facial Images (BMVC 2022)

visinf/style-seqcvae

Diverse Image Captioning with Grounded Style (GCPR 2021)

visinf/benchmarking-synthetic-clones

Is Synthetic Data all We Need? Benchmarking the Robustness of Models Trained with Synthetic Images (CVPR 2024 Workshop on Harnessing Generative Models for Synthetic Visual Datasets)

visinf/jwae

Joint Wasserstein Autoencoders for Aligning Multimodal Embeddings (ICCV 2019 Workshop on Cross-Modal Learning in Real World)

visinf/semantic_lattice

Semantic Lattice (GCPR 2019)

visinf/playing-for-data

Playing for data: Ground Truth from Computer Games (ECCV 2016)

visinf/idsds

Benchmarking the Attribution Quality of Vision Models (NeurIPS)

visinf/mirrorflow

MirrorFlow: Exploiting Symmetries in Joint Optical Flow and Occlusion Estimation (ICCV 2017)

visinf/matryoshka

Matryoshka Networks: Predicting 3D Geometry via Nested Shape Layers

visinf/visinf.github.io

Collection of project pages for publications of the Visual Inference Lab

visinf/interleaved-rtf

Interleaved Regression Tree Field Cascades for Blind Image Deconvolution