Gaussian splatting (GS) for 3D reconstruction has become quite popular due to their fast training, inference speeds and high quality reconstruction. However, GS-based reconstructions generally consist of millions of Gaussians, which makes them hard to use on computationally constrained devices such as smartphones. In this paper, we first propose a principled analysis of advances in efficient GS methods. Then, we propose Trick-GS, which is a careful combination of several strategies including (1) progressive training with resolution, noise and Gaussian scales, (2) learning to prune and mask primitives and SH bands by their significance, and (3) accelerated GS training framework. Trick-GS takes a large step towards resource-constrained GS, where faster run-time, smaller and faster-convergence of models is of paramount concern. Our results on three datasets show that Trick-GS achieves up to 2× faster training, 40× smaller disk size and 2× faster rendering speed compared to vanilla GS, while having comparable accuracy.

Single-view novel view synthesis (NVS) is a notorious problem due to its ill-posed nature, and often requires large, computationally expensive approaches to produce tangible results. In this paper, we propose CheapNVS: a fully end-to-end approach for narrow baseline single-view NVS based on a novel, efficient multiple encoder/decoder design trained in a multi-stage fashion. CheapNVS first approximates the laborious 3D image warping with lightweight learnable modules that are conditioned on the camera pose embeddings of the target view, and then performs inpainting on the occluded regions in parallel to achieve significant performance gains. Once trained on a subset of Open Images dataset, CheapNVS outperforms the state-of-the-art despite being 10× faster and consuming 6% less memory. Furthermore, CheapNVS runs comfortably in real-time on mobile devices, reaching over 30 FPS on a Samsung Tab 9+.

Dense prediction tasks have enjoyed a growing complexity of encoder architectures, decoders, however, have remained largely the same. They rely on individual blocks decoding intermediate feature maps sequentially. We introduce banks, shared structures that are used by each decoding block to provide additional context in the decoding process. These structures, through applying them via resampling and feature fusion, improve performance on depth estimation for state-of-the-art transformer-based architectures on natural and synthetic images whilst training on large-scale datasets.

Performance degradation caused by corrupted multimedia samples is a critical challenge for machine learning models. Previously, three groups of approaches have been proposed to tackle this issue: i) enhancer and denoiser modules to improve the quality of the noisy data, ii) data augmentation approaches, and iii) domain adaptation strategies. All have drawbacks limiting applicability; the first requires paired clean-corrupted data for training and has an high computational cost, while the others can only be used on the same task they were trained on. In this paper, we propose SyMPIE to solve these shortcomings, designing a small, modular, and efficient system to enhance input data for robust downstream multimedia understanding with minimal computational cost. Our SyMPIE is pre-trained on an upstream task/network that should not match the downstream ones and does not need paired clean-corrupted samples. Our key insight is that most input corruptions found in real-world tasks can be modeled through global operations on color channels of images or spatial filters with small kernels. We validate our approach on multiple datasets and tasks, such as image classification (on ImageNetC, ImageNetC-Bar, VizWiz, and a newly proposed mixed corruption benchmark named ImageNetC-mixed) and semantic segmentation (on Cityscapes, ACDC, and DarkZurich) with consistent improvements of about 5% relative accuracy gain across the board1.

Neural Radiance Fields (NeRF) have quickly become the primary approach for 3D reconstruction and novel view synthesis in recent years due to their remarkable performance. Despite the huge interest in NeRF methods, a practical use case of NeRFs has largely been ignored; the exploration of the scene space modelled by a NeRF. In this paper, for the first time in the literature, we propose and formally define the scene exploration framework as the efficient discovery of NeRF model inputs (i.e. coordinates and viewing angles), using which one can render novel views that adhere to user-selected criteria. To remedy the lack of approaches addressing scene exploration, we first propose two baseline methods called Guided-Random Search (GRS) and Pose Interpolation-based Search (PIBS). We then cast scene exploration as an optimization problem, and propose the criteria-agnostic Evolution-Guided Pose Search (EGPS) for efficient exploration. We test all three approaches with various criteria (e.g. saliency maximization, image quality maximization, photo-composition quality improvement) and show that our EGPS performs more favourably than other baselines. We finally highlight key points and limitations, and outline directions for future research in scene exploration.

This paper tackles the problem of semi-supervised video object segmentation on resource-constrained devices, such as mobile phones. We formulate this problem as a distillation task, whereby we demonstrate that small space-time-memory networks with finite memory can achieve competitive results with state of the art, but at a fraction of the computational cost (32 milliseconds per frame on a Samsung Galaxy S22). Specifically, we provide a theoretically grounded framework that unifies knowledge distillation with supervised contrastive representation learning. These models are able to jointly benefit from both pixel-wise contrastive learning and distillation from a pre-trained teacher. We validate this loss by achieving competitive J &F to state of the art on both the standard DAVIS and YouTube benchmarks, despite running up to × 5 faster, and with × 32 fewer parameters.

Document shadow removal is an integral task in document enhancement pipelines, as it improves visibility, readability and thus the overall quality. Assuming that the majority of practical document shadow removal scenarios require real-time, accurate models that can produce high-resolution outputs in-the-wild, we propose Laplacian Pyramid with Input/Output Attention Network (LP-IOANet), a novel pipeline with a lightweight architecture and an upsampling module. Furthermore, we propose three new datasets which cover a wide range of lighting conditions, images, shadow shapes and viewpoints. Our results show that we outperform the state-of-the-art by a 35% relative improvement in mean average error (MAE), while running real-time in four times the resolution (of the state-of-the-art method) on a mobile device.

Convolutional Neural Networks (CNN) are known to exhibit poor generalization performance under distribution shifts. Their generalization have been studied extensively, and one line of work approaches the problem from a frequency-centric perspective. These studies highlight the fact that humans and CNNs might focus on different frequency components of an image. First, inspired by these observations, we propose a simple yet effective data augmentation method HybridAugment that reduces the reliance of CNNs on high-frequency components, and thus improves their robustness while keeping their clean accuracy high. Second, we propose HybridAugment++, which is a hierarchical augmentation method that attempts to unify various frequency-spectrum augmentations. HybridAugment++ builds on HybridAugment, and also reduces the reliance of CNNs on the amplitude component of images, and promotes phase information instead. This unification results in competitive to or better than state-of-the-art results on clean accuracy (CIFAR-10/100 and ImageNet), corruption benchmarks (ImageNet-C, CIFAR-10-C and CIFAR-100-C), adversarial robustness on CIFAR-10 and out-of-distribution detection on various datasets. HybridAugment and HybridAugment++ are implemented in a few lines of code, does not require extra data, ensemble models or additional networks1.

Space-time memory (STM) network methods have been dominant in semi-supervised video object segmentation (SVOS) due to their remarkable performance. In this work, we identify three key aspects where we can improve such methods; i) supervisory signal, ii) pretraining and iii) spatial awareness. We then propose TrickVOS; a generic, method-agnostic bag of tricks addressing each aspect with i) a structure-aware hybrid loss, ii) a simple decoder pretraining regime and iii) a cheap tracker that imposes spatial constraints in model predictions. Finally, we propose a lightweight network and show that when trained with TrickVOS, it achieves competitive results to state-of-the-art methods on DAVIS and YouTube benchmarks, while being one of the first STM-based SVOS methods that can run in real-time on a mobile device.

The majority of the state-of-the-art shadow removal models (SRMs) reconstruct whole input images, where their capacity is needlessly spent on reconstructing non-shadow regions. SRMs that predict residuals remedy this up to a degree, but fall short of providing an accurate and flexible solution. In this paper, we rethink residual predictions and propose Learnable Residual Attention (LRA) and Learnable Dense Reconstruction Attention (LDRA) modules, which operate over the input and the output of SRMs. These modules guide an SRM to concentrate on shadow region reconstruction, and limit reconstruction of non-shadow regions. The modules improve shadow removal (up to 20%) and detection accuracy across various backbones, and even improve the accuracy of other removal methods (up to 10%). In addition, the modules have minimal overhead (+<1MB memory) and are implemented in a few lines of code. Furthermore, to combat the challenge of training SRMs with small datasets, we present a synthetic dataset generation pipeline. Using our pipeline, we create a dataset called PITSA, which has 10 times more unique shadow-free images than the largest benchmark dataset. Pre-training models on the PITSA significantly improves shadow removal (+2 MAE on shadow regions) and detection accuracy of multiple methods. Our results show that LRA&LDRA, when plugged into a lightweight architecture pre-trained on the PITSA, outperform state-of-the-art shadow removal (+0.7 all-region MAE) and detection (+0.1 BER) methods on the benchmark ISTD and SRD datasets, despite running faster (+5%) and consuming less memory (×150).

In many real-world problems, there is typically a large discrepancy between the characteristics of data used in training versus deployment. A prime example is the analysis of aggression videos: in a criminal incidence, typically suspects need to be identified based on their clean portraitlike photos, instead of their prior video recordings. This results in three major challenges; large domain discrepancy between violence videos and ID-photos, the lack of video examples for most individuals and limited training data availability. To mimic such scenarios, we formulate a realistic domain-transfer problem, where the goal is to transfer the recognition model trained on clean posed images to the target domain of violent videos, where training videos are available only for a subset of subjects. To this end, we introduce the "WildestFaces" dataset, tailored to study cross-domain recognition under a variety of adverse conditions. We divide the task of transferring a recognition model from the domain of clean images to the violent videos into two sub-problems and tackle them using (i) stacked affine-transforms for classifier-transfer, (ii) attention-driven pooling for temporal-adaptation. We additionally formulate a self-attention based model for domain-transfer. We establish a rigorous evaluation protocol for this "clean-to-violent" recognition task, and present a detailed analysis of the proposed dataset and the methods. Our experiments highlight the unique challenges introduced by the WildestFaces dataset and the advantages of the proposed approach.