Guiding monocular depth estimation using Depth-Attention Volume, achieving state-of-the-art on NYU-Depth-v2.

Lam Huynh, Phong Nguyen-Ha, Jiri Matas et al.

Introduces affine skip connections in GNNs, inspired by RBF interpolation, improving shape reconstruction and classification with 8% error reduction.

Shunwang Gong, Mehdi Bahri, Michael M. Bronstein et al.

Using entmax for training and sampling, reducing mismatch, improving diversity and coherence in text generation.

Pedro Henrique Martins, Zita Marinho, André F. T. Martins

A patch-based fully convolutional GAN generated realistic HMX microstructures and controllable porosity, matching 9.5-GPa hot-spot dynamics.

Sehyun Chun, Sidhartha Roy, Yen Thi Nguyen et al.

Proposed Anisotropic Convolutional Network (AIC-Net) improves 3D semantic scene completion accuracy on NYU-Depth-v2.

Jie Li, Kai Han, Peng Wang et al.

PointGroup achieves 63.6% mAP50 on ScanNet v2 using dual-set clustering for 3D instance segmentation.

Li Jiang, Hengshuang Zhao, Shaoshuai Shi et al.

Proposes CutBlur, a novel data augmentation for image super-resolution, combining low-high resolution patch cut-and-paste, improving PSNR by up to 0.27dB on RealSR.

Jaejun Yoo, Namhyuk Ahn, Kyung-Ah Sohn

Physics-based NLOS 3D human pose estimation from transient photon histograms, leveraging deep reinforcement learning and learnable PSF for robust performance.

Mariko Isogawa, Ye Yuan, Matthew O'Toole et al.

TartanAir provides a large-scale, multi-modal synthetic dataset with challenging environments to advance visual SLAM robustness.

Wenshan Wang, Delong Zhu, Xiangwei Wang et al.

Deep Geometric Functional Maps excel in shape correspondence, achieving high accuracy with less training data.

Nicolas Donati, Abhishek Sharma, Maks Ovsjanikov

Proposed 3D Sketch-aware Semantic Scene Completion method improves SSC task performance by 7.8% on NYU dataset.

Xiaokang Chen, Kwan-Yee Lin, Chen Qian et al.

Proposes SPARQA, a skeleton-based semantic parser, achieving 21.53 F1 on GraphQuestions and 31.57 P@1 on ComplexWebQuestions, outperforming SOTA.

Yawei Sun, Lingling Zhang, Gong Cheng et al.

Open-source TensorFlow tool supports hyperspectral image augmentation with 13 channels, boosting remote sensing model accuracy.

Mohamed Abdelhack

Using ν-Gap based dynamics similarity and Bayesian optimization, the proposed method efficiently selects source experiences, improving target robot performance by 62%.

Michael J. Sorocky, Siqi Zhou, Angela P. Schoellig

Proposes a physics-based CMOS sensor noise model for realistic low-light RAW denoising, achieving performance comparable to real-data training.

Kaixuan Wei, Ying Fu, Jiaolong Yang et al.

AiiDA 1.0 achieves high-throughput automated workflows with full data provenance, supporting tens of thousands of processes per hour.

Sebastiaan. P. Huber, Spyros Zoupanos, Martin Uhrin et al.

Introduced TextCaps dataset with 145k captions for 28k images, integrating OCR and visual reasoning for advanced image captioning.

Oleksii Sidorov, Ronghang Hu, Marcus Rohrbach et al.

Using symmetry and bifurcation theory, the paper derives power series expansions of critical points in shallow ReLU networks, revealing different loss decay behaviors of spurious minima.

Yossi Arjevani, Michael Field

Proposes a CVaR-based submodular optimization algorithm with theoretical guarantees for risk-aware multi-robot coordination.

Lifeng Zhou, Pratap Tokekar

Study minimax optimal methods for label shift in non-parametric settings, revealing difficulty differences between supervised and unsupervised scenarios.

Subha Maity, Yuekai Sun, Moulinath Banerjee