Factorized Multi-Resolution HashGrid for Efficient Neural Radiance Fields: Execution on Edge-Devices

Kim Jun-Seong; Mingyu Kim; GeonU Kim; Tae-Hyun Oh; Jin-Hwa Kim

cs.CVApr 3, 2026

Factorized Multi-Resolution HashGrid for Efficient Neural Radiance Fields: Execution on Edge-Devices

Authors: Kim Jun-Seong, Mingyu Kim, GeonU Kim, Tae-Hyun Oh, Jin-Hwa Kim

Organizations: Dept. of E.E., POSTECH · Dept. of CS, The Univ. of British Columbia · Grad. School of AI, POSTECH · School of Computing Engineering, KAIST ·

Abstract

We introduce Fact-Hash, a novel parameter-encoding method for training on-device neural radiance fields. Neural Radiance Fields (NeRF) have proven pivotal in 3D representations, but their applications are limited due to large computational resources. On-device training can open large application fields, providing strength in communication limitations, privacy concerns, and fast adaptation to a frequently changing scene. However, challenges such as limited resources (GPU memory, storage, and power) impede their deployment. To handle this, we introduce Fact-Hash, a novel parameter-encoding merging Tensor Factorization and Hash-encoding techniques. This integration offers two benefits: the use of rich high-resolution features and the few-shot robustness. In Fact-Hash, we project 3D coordinates into multiple lower-dimensional forms (2D or 1D) before applying the hash function and then aggregate them into a single feature. Comparative evaluations against state-of-the-art methods demonstrate Fact-Hash's superior memory efficiency, preserving quality and rendering speed. Fact-Hash saves memory usage by over one-third while maintaining the PSNR values compared to previous encoding methods. The on-device experiment validates the superiority of Fact-Hash compared to alternative positional encoding methods in computational efficiency and energy consumption. These findings highlight Fact-Hash as a promising solution to improve feature grid representation, address memory constraints, and improve quality in various applications. Project page: https://facthash.github.io/

Figures & tables

Fig. 1: Comparison of Instant-ngp [ 16 ] , TensoRF [ 14 ] , K-planes [ 15 ] and Ours in terms of PSNR and inference time on the edge-device. Training is conducted on a standard GPU machine, whereas the inference is performed on the edge-device aligning with standard edge-device utilization practices. The area of each circle represents the model size.

Fig. 2: Conceptual illustration of parameter-encoding; iNGP [ 16 ] , TensoRF [ 14 ] , K-planes [ 15 ] and the proposed method.

Fig. 3: Schematic of the proposed method, Fact-Hash. For a given point $P$ , we first project the point into the tri-plane and obtain surrounding multi-resolution 2D indices of each plane. For the multi-resolution 2D indices, we lookup the corresponding features from the assigned hash tables, and perform bi-linear interpolation to compose 3 multi-resolution feature vectors $f_{xy},f_{yz},$ and $f_{zx}$ . The interpolated feature vectors are multiplied with Hadamard product and decoded to the density $\sigma$ and the color $c$ with the shallow MLP decoders. We predict the color of ray using standard volumetric rendering formula with the densities and the colors along the ray and minimize the reconstruction loss with the regularization.

Case	Model			Avg. PSNR $\uparrow$	Avg. SSIM $\uparrow$	Avg. LPIPS $\downarrow$
Case	Name	#Params (M) $\downarrow$	Size $\downarrow$ (Mb)	Avg. PSNR $\uparrow$	Avg. SSIM $\uparrow$	Avg. LPIPS $\downarrow$
Full views	iNGP	11.46	45.24	31.59	0.953	0.061
	TensoRF	17.38	68.69	32.88	0.961	0.028
	K-planes	33.04	393.08	32.36	0.962	0.049
	TensoRF	6.51	25.73	31.69	0.951	0.064
	K-planes	16.53	64.82	32.06	0.956	0.057

TABLE I: Experimental results on the NeRF synthetic datasets.

Fig. 4: Qualitative results of 8 views case on the NeRF synthetic dataset. Rendered images are results of chair , hotdog cases in the NeRF synthetic dataset by iNGP, TensoRF, K-planes, and ours.

Fig. 5: PSNR (a) and SSIM (b) values according to the number of uniformly sampled inputs. All metrics are average value of 7 NeRF synthetic data.

Fig. 6: Visualization of bitfield on the NeRF synthetic dataset. Each case is trained on 8-views on chair , drums and hotdog .

Model	10 Watt $\downarrow$									20 Watt Avg. $\downarrow$
Model	chair	drums	ficus	hotdog	lego	materials	mic	ship	Avg.	20 Watt Avg. $\downarrow$
iNGP	71.8	142.3	507.0	167.4	126.3	251.3	96.9	566.6	241.2	191.4
TensoRF	109.5	199.8	174.3	199.2	188.4	395.6	149.0	641.1	257.1	219.6
K-Planes	97.8	195.8	159.1	206.4	167.8	339.3	122.1	504.7	224.1	185.9
Ours	93.7	164.5	145.1	130.7	161.8	319.1	89.6	229.8	166.8	133.2

TABLE II: rendering time for 200 images on the NeRF synthetic datasets.

Case	Model			Avg. PSNR $\uparrow$	Avg. SSIM $\uparrow$	Avg. LPIPS $\downarrow$
Case	Name	#Params (M) $\downarrow$	Size $\downarrow$ (Mb)	Avg. PSNR $\uparrow$	Avg. SSIM $\uparrow$	Avg. LPIPS $\downarrow$
Full views	iNGP	11.46	44.18	28.05	0.918	0.128
	TensoRF	4.89	18.92	27.93	0.912	0.139
	K-planes	16.53	63.30	28.40	0.923	0.120
	Ours	3.40	13.22	28.42	0.919	0.121
10% views	iNGP	11.46	44.18	19.73	0.869	0.186

TABLE III: Experimental results on the tank and temples datasets.

Fig. 7: Qualitative results on the Tank and Temples for 10% training inputs.

Fig. 8: Qualitative results on the San Francisco Mission Bay dataset. For 1/3 views, we conduct the experiment with the default size of baselines [ 16 , 13 ] and use 1/3 number of images from the dataset for training. For Full views, we constrain the model sizes to $\approx$ 50 Mb and train in the full-view setting.

Fig. 9: Comparison between iNGP and Fact-Hash in various collision rate. PSNR values are averaged along the scenes where iNGP success in training, excluding hotdog, lego, materials .

Fig. 10: Ablation study on encoding methods.

Neural Radiance Fields

Neural radiance fields represent 3D scenes as continuous functions of position and viewing direction to synthesize images from new camera views.

See all 82 papers

Hash-QNeRF: Multiresolution Hash Encoding for Quantum Neural Radiance Fields
Jul 23, 2026Digonto Biswas, Tana Ballove, Anjan Bandyopadhyay +2Neural Rendering Hybrid Quantum-Classical ML
Centres of Innovation and Research KIIT Deemed to be University Bhubaneswar, India
Low-Cost Neural Radiance Fields
May 10, 2026Alice Huang, Prathamesh Sonawane, Yashdeep Thorat +1Neural Rendering Sparse-View 3D Reconstruction
University of Illinois Urbana Champaign
Eulerian Gaussian Splatting using Hashed Probability Pyramids
May 27, 2026Mia Gaia Polansky, George Kopanas, Stephan Garbin +23D Gaussian Splatting Neural Rendering
Harvard University · Google DeepMind · Google

Jul 23, 2026J/K move · Enter open · S save

Hash-QNeRF: Multiresolution Hash Encoding for Quantum Neural Radiance Fields

Digonto Biswas, Tana Ballove, Anjan Bandyopadhyay, Sutanu Mangal+1

Centres of Innovation and Research KIIT Deemed to be University Bhubaneswar, India

Neural Rendering Hybrid Quantum-Classical ML Neural Radiance Fields

Open paper AskPDF arXiv

Neural Radiance Fields (NeRF) have revolutionized novel view synthesis, yet their classical implementations remain computationally intensive for high-fidelity rendering. QNeRF recently demonstrated the feasibility of training NeRF on gate-based quantum computers by combining amplitude embedding, parameterized quantum circuits (PQCs), parity-based measurements, and volumetric rendering. However, QNeRF relies on classical sinusoidal positional encoding for spatial coordinates, which scales poorly with scene complexity and resolution. In this work, we replace the sinusoidal positional encoding for spatial coordinates with the multiresolution hash encoding from Instant-NGP while keeping the view-direction encoding, amplitude MLP, quantum circuit, parity measurement, output scaling, and volumetric rendering pipeline unchanged. This hybrid design, Hash-QNeRF, retains the quantum radiance prediction step while benefiting from the fast convergence and memory efficiency of learnable hash grids. On a synthetic Blender scene, we achieve a final training loss of 0.003534, corresponding to approximately 24.5 dB PSNR on the fitted batch. Noise resilience experiments using Qiskit FakeKyiv and FakeTorino backends yield state fidelities of 0.93 to 0.98, indicating that hash encoding does not degrade the quantum circuit's noise tolerance.

Abstract

Neural Radiance Fields

Explore similar work

Hash-QNeRF: Multiresolution Hash Encoding for Quantum Neural Radiance Fields

Low-Cost Neural Radiance Fields

Eulerian Gaussian Splatting using Hashed Probability Pyramids