Robert Laganière | Searcharxiv

arXiv2026

Physics-Aware Diffusion for LiDAR Point Cloud Densification

LiDAR perception is severely limited by the distance-dependent sparsity of distant objects. While diffusion models can recover dense geometry, they suffer from prohibitive latency and physical hallucinations manifesting as ghost points. We propose Scanline-Consistent Range-Aware Diffusion, a framework that treats densification as probabilistic refinement rather than generation. By leveraging Partial Diffusion (SDEdit) on a coarse prior, we achieve high-fidelity results in just 156ms. Our novel Ray-Consistency loss and Negative Ray Augmentation enforce sensor physics to suppress artifacts. Our method achieves state-of-the-art results on KITTI-360 and nuScenes, directly boosting off-the-shelf 3D detectors without retraining. Code will be made available.

cs.CV↗

arXiv2019

A Curious Link Between Prime Numbers, the Maundy Cake Problem and Parallel Sorting

We present new theoretical algorithms that sums the n-ary comparators output in order to get the permutation indices in order to sort a sequence. By analysing the parallel ranking algorithm, we found that the special comparators number of elements it processes divide the number of elements to be sorted. Using the divide and conquer method, we can express the sorting problem into summing output of comparators taking a prime number of elements, given that this prime number divides the initial disordered sequence length. The number of sums is directly related to the Maundy cake problem. Furthermore, we provide a new sequence that counts the number of comparators used in the algorithms.

cs.DS↗

arXiv2019

Application of DenseNet in Camera Model Identification and Post-processing Detection

Camera model identification has earned paramount importance in the field of image forensics with an upsurge of digitally altered images which are constantly being shared through websites, media, and social applications. But, the task of identification becomes quite challenging if metadata are absent from the image and/or if the image has been post-processed. In this paper, we present a DenseNet pipeline to solve the problem of identifying the source camera-model of an image. Our approach is to extract patches of 256*256 from a labeled image dataset and apply augmentations, i.e., Empirical Mode Decomposition (EMD). We use this extended dataset to train a Neural Network with the DenseNet-201 architecture. We concatenate the output features for 3 different sizes (64*64, 128*128, 256*256) and pass them to a secondary network to make the final prediction. This strategy proves to be very robust for identifying the source camera model, even when the original image is post-processed. Our model has been trained and tested on the Forensic Camera-Model Identification Dataset provided for the IEEE Signal Processing (SP) Cup 2018. During testing we achieved an overall accuracy of 98.37%, which is the current state-of-the-art on this dataset using a single model. We used transfer learning and tested our model on the Dresden Database for Camera Model Identification, with an overall test accuracy of over 99% for 19 models. In addition, we demonstrate that the proposed pipeline is suitable for other image-forensic classification tasks, such as, detecting the type of post-processing applied to an image with an accuracy of 96.66% -- which indicates the generality of our approach.

eess.IV↗