papers

Publications (16)

cs.CV2020

Footprints and Free Space from a Single Color Image

Jamie Watson, Michael Firman, Aron Monszpart +1

Understanding the shape of a scene from a single color image is a formidable computer vision task. However, most methods aim to predict the geometry of surfaces that are visible to…

cs.CV2024

AirPlanes: Accurate Plane Estimation via 3D-Consistent Embeddings

Jamie Watson, Filippo Aleotti, Mohamed Sayed +5

Extracting planes from a 3D scene is useful for downstream tasks in robotics and augmented reality. In this paper we tackle the problem of estimating the planar surfaces in a scene…

cs.CV2019

Digging Into Self-Supervised Monocular Depth Estimation

Clément Godard, Oisin Mac Aodha, Michael Firman +1

Per-pixel ground-truth depth data is challenging to acquire at scale. To overcome this limitation, self-supervised learning has emerged as a promising alternative for training mode…

cs.CV2016

RGBD Datasets: Past, Present and Future

Michael Firman

Since the launch of the Microsoft Kinect, scores of RGBD datasets have been released. These have propelled advances in areas from reconstruction to gesture recognition. In this pap…

cs.CV2022

Removing Objects From Neural Radiance Fields

Silvan Weder, Guillermo Garcia-Hernando, Aron Monszpart +4

Neural Radiance Fields (NeRFs) are emerging as a ubiquitous scene representation that allows for novel view synthesis. Increasingly, NeRFs will be shareable with other people. Befo…

cs.CV2025

MVSAnywhere: Zero-Shot Multi-View Stereo

Sergio Izquierdo, Mohamed Sayed, Michael Firman +6

Computing accurate depth from multiple views is a fundamental and longstanding challenge in computer vision. However, most existing approaches do not generalize well across differe…

cs.CV2025

Complete Gaussian Splats from a Single Image with Denoising Diffusion Models

Ziwei Liao, Mohamed Sayed, Steven L. Waslander +3

Gaussian splatting typically requires dense observations of the scene and can fail to reconstruct occluded and unobserved areas. We propose a latent diffusion model to reconstruct…

cs.CV2023

Virtual Occlusions Through Implicit Depth

Jamie Watson, Mohamed Sayed, Zawar Qureshi +4

For augmented reality (AR), it is important that virtual assets appear to `sit among' real world objects. The virtual element should variously occlude and be occluded by real matte…

cs.CV2021

Single Image Depth Prediction with Wavelet Decomposition

Michaël Ramamonjisoa, Michael Firman, Jamie Watson +2

We present a novel method for predicting accurate depths from monocular images with high efficiency. This optimal efficiency is achieved by exploiting wavelet decomposition, which…

cs.CV2020

DiverseNet: When One Right Answer is not Enough

Michael Firman, Neill D. F. Campbell, Lourdes Agapito +1

Many structured prediction tasks in machine vision have a collection of acceptable answers, instead of one definitive ground truth answer. Segmentation of images, for example, is s…

cs.CV2022

SimpleRecon: 3D Reconstruction Without 3D Convolutions

Mohamed Sayed, John Gibson, Jamie Watson +3

Traditionally, 3D indoor scene reconstruction from posed images happens in two phases: per-image depth estimation, followed by depth merging and surface reconstruction. Recently, a…

cs.CV2021

The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth

Jamie Watson, Oisin Mac Aodha, Victor Prisacariu +2

Self-supervised monocular depth estimation networks are trained to predict scene depth using nearby frames as a supervision signal during training. However, for many applications,…

cs.CV2021

Panoptic Segmentation Forecasting

Colin Graber, Grace Tsai, Michael Firman +2

Our goal is to forecast the near future given a set of recent observations. We think this ability to forecast, i.e., to anticipate, is integral for the success of autonomous agents…

cs.CV2019

Self-Supervised Monocular Depth Hints

Jamie Watson, Michael Firman, Gabriel J. Brostow +1

Monocular depth estimators can be trained with various forms of self-supervision from binocular-stereo data to circumvent the need for high-quality laser scans or other ground-trut…

cs.CV2024

DoubleTake: Geometry Guided Depth Estimation

Mohamed Sayed, Filippo Aleotti, Jamie Watson +5

Estimating depth from a sequence of posed RGB images is a fundamental computer vision task, with applications in augmented reality, path planning etc. Prior work typically makes us…

cs.CV2020

Learning Stereo from Single Images

Jamie Watson, Oisin Mac Aodha, Daniyar Turmukhambetov +2

Supervised deep networks are among the best methods for finding correspondences in stereo image pairs. Like all supervised approaches, these networks require ground truth data duri…