Peter Kocsis

4 papers · 2022–2026 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (10)

Venues

CVPR (3) NeurIPS (1)

Top co-authors

Matthias Nießner (3) Lukas Höllein (1) Laura Leal-Taixé (1) Ismail Elezi (1) Matthias Niessner (1) Julien Philip (1) Guillem Braso (1) Peter Súkeník (1) Kalyan Sunkavalli (1) Vincent Sitzmann (1)

Research topics

Computer Vision (3) Deep Learning (3) Models (3) Analysis (2) Generation (2) Processing (2) Machine Learning (1) Application Areas (1) Core Methods (1) Learning Types (1)

Keywords

diffusion model (3) image generation (1) knowledge distillation (1) generative model (1) convolutional neural network (1) material estimation (1) multi-view image (1) indoor scene (1) fully connected layer (1) intrinsic image decomposition (1) shading estimation (1) normal map (1) appearance decomposition (1) material reconstruction (1) illumination control (1) low-data regime (1) albedo prediction (1) inverse path tracing (1) active learning (1) material disentanglement (1)

Papers

Intrinsic Image Fusion for Multi-View 3D Material Reconstruction CVPR 2026 Intrinsic Image Diffusion for Indoor Single-view Material Estimation CVPR 2024 LightIt: Illumination Modeling and Control for Diffusion Models CVPR 2024 The Unreasonable Effectiveness of Fully-Connected Layers for Low-Data Regimes NeurIPS 2022