Diffusion Model for Dense Matching

Authors: Jisu Nam, Gyuseong Lee, Sunwoo Kim, Hyeonsu Kim, Hyoungwon Cho, Seyeon Kim, Seungryong Kim

ICLR 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our experimental results demonstrate significant performance improvements of our method over existing approaches, and the ablation studies validate our design choices along with the effectiveness of each component.
Researcher Affiliation Collaboration 1Korea University 2LG Electronics 3KT
Pseudocode No The paper describes the model and processes using mathematical equations and textual descriptions, but it does not include a clearly labeled pseudocode or algorithm block.
Open Source Code Yes Code and pretrained weights are available at https://ku-cvlab.github.io/Diff Match.
Open Datasets Yes We conducted comprehensive experiments in geometric matching for four datasets: HPatches (Balntas et al., 2017), ETH3D (Schops et al., 2017), Image Net-C (Hendrycks & Dietterich, 2019) corrupted HPatches and Image Net-C corrupted ETH3D.
Dataset Splits No The paper mentions training on DPED-City Scape-ADE and COCO-augmented DPED-City Scape-ADE, and evaluating on HPatches and ETH3D, but it does not specify explicit training, validation, and test splits (e.g., percentages or sample counts) for these datasets.
Hardware Specification Yes All our experiments were conducted on 6 24GB RTX 3090 GPUs.
Software Dependencies No The paper states, 'We implemented the network in Py Torch (Paszke et al., 2019) and used the Adam W optimizer (Loshchilov & Hutter, 2017),' but it does not specify the version numbers for PyTorch or other libraries used for implementation.
Experiment Setup Yes For the denoising diffusion model, we train 121M modified U-Net based on (Nichol & Dhariwal, 2021) with the learning rate to 1 10 4 and trained the model for 130,000 iterations with a batch size of 24. For the flow upsampling diffusion model, we used a learning rate of 3 10 5 and finetuned the pretrained conditional denoising diffusion model for 20,000 iterations with a batch size of 2.