Improved 3D scene understanding from partial point sets using multiview fusion.
problem Challenging task of 3D scene semantic understanding from partial point clouds.
method Multiview representation of 360° point clouds and fusion with original data.
result Overall increase of 31.9% and 4.3% in segmentation accuracy for partial and complete scenes.
Pix2Shape learns 3D scene representations from single images without supervision.
problem Learning 3D scene information from a single image without supervision.
method Pix2Shape uses an encoder, decoder, and critic network to generate 2.5D surfel-based reconstructions.
result Pix2Shape can generate complex 3D scenes from a single image, scaling with on-screen resolution.
New dataset tests mental rotation from single images, improving model understanding of 3D scenes.
problem Understanding how a scene looks from a different viewpoint using a single image.
method Created CLEVR-MRT dataset, explored neural architectures for volumetric scene representations.
result Demonstrated the effectiveness of volumetric representations in answering mental rotation questions.
BPI models 2D patterns on multiple planes and 3D scene from a single image.
problem Understanding and editing images with multiple 2D planes and 3D scene from a single image.
method Box Program Induction (BPI) with neural networks and search-based algorithm.
result Holistic, structured scene representation enables 3D-aware image editing.
GIBLy adds geometric priors to 3D segmentation models, improving performance with minimal overhead.
problem Lack of explicit geometric information in 3D semantic segmentation models.
method Introduces GIBLy, a lightweight geometric inductive bias layer that integrates learnable geometric priors into existing 3D segmentation pipelines.
result Consistent performance gains across multiple benchmarks, including up to +11.5% mIoU on TS40K with PTV3.
A neural scene representation framework enforcing 3D transformations.
problem Learning 3D scene representations from images without 3D supervision.
method Introducing a loss enforcing equivariance of the scene representation with 3D transformations.
result Real-time neural rendering with comparable results to models requiring minutes for inference.
ROOTS learns to represent and render 3D scenes with object-centric models.
problem Learning to represent and render 3D scenes with object-centric compositionality.
method Probabilistic generative model for learning object representations and scene rendering from partial observations.
result The model can infer 3D object representations and render scenes from arbitrary viewpoints.
Generative Multisensory Network learns 3D scene representations from multiple modalities.
problem Learning robust 3D scene representations from multiple sensory modalities.
method Amortized Product-of-Experts for efficient inference and cross-modal generation.
result The model can infer modality-invariant 3D scene representations efficiently from various sensory modalities.
Generates coherent 3D scenes from monocular videos without supervision.
problem Lack of 3D scene modeling in video generation models.
method Trains a model to generate 3D scenes with moving objects and a background from monocular videos.
result Trained model generates coherent 3D scenes with multiple moving objects and a background.
NeRF-VAE generates 3D scenes with geometric structure from few images.
problem Generating 3D scenes from few images with geometric consistency.
method Combines NeRF and VAE, incorporating shared geometric structure.
result NeRF-VAE can infer and render geometrically-consistent scenes from unseen environments.
We propose a systematic learning-based approach to the generation of massive quantities of synthetic 3D scenes and arbitrary numbers of photorealistic 2D images thereof, with associated ground truth information, for the purposes of training, benchmarking, and diagnosing learning-based computer vision and robotics algor…
Real-time scene understanding solved using Approximate Bayesian Computation.
problem Predicting human actions, object poses, and pedestrian crossings from depth images.
method Bayesian error model, neural surrogates, and adaptive discretization.
result Real-time inference on real-world problems is feasible.
Enhances neural rendering with geometry-aware attention.
problem Efficiently modeling complex 3D scenes.
method Introduces Epipolar Cross Attention (ECA) for non-local operations.
result Significant improvement in Generative Query Networks (GQN) performance.
ObSuRF converts a single image into a 3D model with NeRFs.
problem Creating a 3D model from a single image with object segmentation.
method Unsupervised volume segmentation using Neural Radiance Fields (NeRFs).
result ObSuRF can segment a 3D scene into objects from a single image.
GENESIS generates and samples 3D scenes by capturing object interactions.
problem Lack of models that explicitly capture object interactions in scene generation.
method Object-centric latent variables, spatial GMM, amortized inference, autoregressive prior.
result First object-centric generative model of 3D visual scenes.
Improves AI agents' 3D navigation by learning from failures and 3D spatial relationships.
problem Challenges in data efficiency, obstacle avoidance, and generalization in 3D visual navigation.
method Incorporates attention on 3D spatial relationships and a target skill extension module into DRL framework.
result Significantly improves navigation performance and generalization across targets and scenes.
SCENE-Net improves 3D point cloud segmentation with low resource usage and transparency.
problem Lack of resources and transparency in 3D semantic segmentation models.
method SCENE-Net uses signature shapes identified via GENEOs to achieve semantic segmentation with minimal resources.
result SCENE-Net achieves comparable IoU to state-of-the-art methods with less data and computational resources.
MONet learns to decompose scenes into meaningful components without supervision.
problem Learning meaningful scene decompositions without labeled data.
method MONet combines a VAE and recurrent attention network to learn decompositions of 3D scenes.
result MONet can learn to represent 3D scenes into meaningful components like objects and background.
We consider learning based methods for visual localization that do not require the construction of explicit maps in the form of point clouds or voxels. The goal is to learn an implicit representation of the environment at a higher, more abstract level. We propose to use a generative approach based on Generative Query N…
We consider the problem of learning object arrangements in a 3D scene. The key idea here is to learn how objects relate to human poses based on their affordances, ease of use and reachability. In contrast to modeling object-object relationships, modeling human-object relationships scales linearly in the number of objec…
Efficient model for foggy scene understanding in vehicles.
problem Challenging scene understanding and segmentation under foggy conditions.
method Domain adaptation and illumination-invariant image transformation.
result Outperforms state-of-the-art models in foggy scene understanding.
SNP extends Neural Processes to handle temporal dependencies in sequences.
problem Handling temporal dependencies in sequences of stochastic processes.
method Integrates a temporal state-transition model into Neural Processes.
result First 4D model capable of dynamic 3D scene modeling.
Recently, multiple formulations of vision problems as probabilistic inversions of generative models based on computer graphics have been proposed. However, applications to 3D perception from natural images have focused on low-dimensional latent scenes, due to challenges in both modeling and inference. Accounting for th…
ED-NeRF efficiently edits 3D scenes using latent space NeRF and improved loss functions.
problem Slow training speeds and inadequate editing loss functions in existing NeRF editing techniques.
method Embedding real-world scenes into latent space of LDM, using a unique refinement layer and an improved loss function.
result ED-NeRF achieves faster editing speed and improved output quality compared to state-of-the-art models.
New framework segments 3D scenes using neural algorithms and sub-Riemannian geometry.
problem Effective scene segmentation in 3D vision.
method Neurogeometric sub-Riemannian model, harmonic analysis, neural-based stereo correspondence.
result Sub-Riemannian metric is central to effective scene segmentation.
In this paper we propose a unified framework for structured prediction with latent variables which includes hidden conditional random fields and latent structured support vector machines as special cases. We describe a local entropy approximation for this general formulation using duality, and derive an efficient messa…
Generates garden paintings from text descriptions using deep learning.
problem Lack of firsthand material for traditional Chinese garden reconstruction.
method Deep learning model trained on text and paintings of Ming Dynasty gardens.
result Model generates garden paintings in Ming Dynasty style based on textual descriptions.
SPACE models complex scenes by decomposing objects and backgrounds.
problem Scalability and unsupervised object-oriented scene representation learning.
method Generative latent variable model combining spatial-attention and scene-mixture approaches.
result SPACE achieves factorized object representations and decomposes complex scenes.
Proposes Deep Scenes for interaction-aware scene understanding in reinforcement learning for autonomous driving.
problem Leveraging deep reinforcement learning for high-level decision making in autonomous driving requires handling variable-length sequences of different object types and interactions.
method Introduces Deep Scenes architecture, an extension of Deep Sets or Graph Convolutional Networks, to learn complex interaction-aware scene representations.
result Graph-Q and DeepScene-Q algorithms outperform state-of-the-art methods in evaluations with SUMO.
Proposes local coordinate frames for improving model performance in complex dynamical systems.
problem Improving model performance in complex, non-linear, and time-dependent dynamical systems.
method Introduces roto-translation invariant local coordinate frames for geometric graphs.
result The approach outperforms state-of-the-art models in various complex scenarios.
The paper proposes a model to forecast traffic motion from sensor data.
problem Accurately predicting traffic motion for safe vehicle maneuvers.
method Implicit latent variable model using interaction graphs and graph neural networks.
result Achieves state-of-the-art motion forecasting and interaction understanding.
Scene understanding remains a significant challenge in the computer vision community. The visual psychophysics literature has demonstrated the importance of interdependence among parts of the scene. Yet, the majority of methods in computer vision remain local. Pictorial structures have arisen as a fundamental parts-bas…
Scene text magnifier enhances readability for visually impaired.
problem Helps visually impaired read natural scene text.
method Four CNN-based networks: character erasing, extraction, magnify, synthesis.
result Effective text magnification without background alteration.
Energy-based models can generate complex images by combining simpler concepts.
problem Generating natural images that satisfy complex logical combinations of concepts.
method Energy-based models combine probability distributions of simpler concepts to generate compositions.
result Energy-based models can generate images that satisfy conjunctions, disjunctions, and negations of concepts.
Stochastic video prediction models take in a sequence of image frames, and generate a sequence of consecutive future image frames. These models typically generate future frames in an autoregressive fashion, which is slow and requires the input and output frames to be consecutive. We introduce a model that overcomes the…
A new method to decompose audio scenes using deep learning.
problem Understanding audio scenes with random microphone arrangements.
method Formulated a neural network for nonnegative tensor factorization.
result Learned sources' individual spectral dictionaries and activation patterns.
Paper simplifies deep RL for mobile robots on consumer hardware.
problem Training complex reasoning agents in 3D environments.
method Used ViZDoom for fast simulation and varied difficulty scenarios.
result Robust baseline agent architecture trained on consumer hardware.
A novel method for visual question answering using scene graphs and reinforcement learning.
problem Answering free-form questions about images with deep linguistic and visual understanding.
method Context-driven, sequential reasoning based on scene graphs and reinforcement learning.
result Our method almost reaches human performance on the GQA dataset.
A model learns object representations for physical scene understanding without direct supervision.
problem Learning object-centric representations without direct supervision of object properties.
method Object-Oriented Prediction and Planning (O2P2) model that learns perception, physics interaction, and rendering functions.
result The model can predict physical interactions and build block towers more complex than those seen during training.
We propose an automatic method to infer high dynamic range illumination from a single, limited field-of-view, low dynamic range photograph of an indoor scene. In contrast to previous work that relies on specialized image capture, user input, and/or simple scene models, we train an end-to-end deep neural network that di…
3D adversarial logos can fool object detectors in real-world settings.
problem Creating robust adversarial attacks in 3D rendering views.
method Constructing 3D adversarial logos via texture mapping and differentiable rendering.
result 3D adversarial logos are more versatile and robust than traditional adversarial patches.
Machine understanding of complex images is a key goal of artificial intelligence. One challenge underlying this task is that visual scenes contain multiple inter-related objects, and that global context plays an important role in interpreting the scene. A natural modeling framework for capturing such effects is structu…
Deep network predicts action sequences for complex tasks from a scene image.
problem Scalable task and motion planning from initial scene images.
method Deep convolutional recurrent neural network that predicts action sequences.
result Predicts promising action sequences, reducing motion planning problems.
nuScenes dataset includes multimodal sensor data for autonomous vehicle training.
problem Training robust detection and tracking methods for autonomous vehicles.
method Presented the first multimodal dataset with 6 cameras, 5 radars, and 1 lidar, 360-degree field of view.
result 7x more annotations and 100x more images than KITTI dataset.
In microsurgery, lasers have emerged as precise tools for bone ablation. A challenge is automatic control of laser bone ablation with 4D optical coherence tomography (OCT). OCT as high resolution imaging modality provides volumetric images of tissue and foresees information of bone position and orientation (pose) as we…
New text-to-image diffusion models improve scene understanding for AI agents.
problem Fine-grained scene understanding for AI agents from text and images.
method Pre-trained text-to-image diffusion models optimized for generating images from text prompts.
result Policies learned with Stable Control Representations outperform state-of-the-art approaches on various control tasks.
Visual relationship detection can bridge the gap between computer vision and natural language for scene understanding of images. Different from pure object recognition tasks, the relation triplets of subject-predicate-object lie on an extreme diversity space, such as \textit{person-behind-person} and \textit{car-behind…
Generative model improves scene graph prediction for rare compositions.
problem Challenges in inferring unseen or rare scene graph compositions.
method Synthesizing rare scene graphs by perturbing real ones, using conditional GANs.
result Marginal but consistent improvements in zero- and few-shot metrics.